© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 59141
    Prev
    Next
    INDEX
    Explanations

    bonds

    np_max-act · gemini-2.0-flash

    The neuron detects references to chemical bonding, firing strongly on words like “bond,” “bonding,” “covalent,” “dissociation,” and related bond‐focused terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms and concepts related to chemical bonding, particularly focusing on ionic and covalent bonds.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .dst
    -0.07
     उत
    -0.06
    >>>
    -0.06
     ощ
    -0.06
    Doctors
    -0.06
     conscious
    -0.06
    	where
    -0.06
     пром
    -0.06
    farm
    -0.06
     skew
    -0.06
    POSITIVE LOGITS
    MEDIA
    0.07
     Bond
    0.07
    argar
    0.07
     Luxury
    0.06
    仕
    0.06
     신규
    0.06
     polygon
    0.06
     связи
    0.06
    uebas
    0.06
    _command
    0.06
    Activations Density 0.004%

    No Known Activations