© 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. 59059
    Prev
    Next
    INDEX
    Explanations

    dna double helix

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of “hel” chunks—i.e. mentions of helix‐related terms (especially “double helix”) and closely associated molecular-structure vocabulary.

    oai_token-act-pair · o4-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
     Ott
    -0.07
    defined
    -0.06
    Kim
    -0.06
    .Enc
    -0.06
     Kim
    -0.06
    nému
    -0.06
     Herbal
    -0.06
    -network
    -0.06
     eliminated
    -0.06
    eru
    -0.06
    POSITIVE LOGITS
     Про
    0.07
     تخصص
    0.06
    steam
    0.06
    alleries
    0.06
     pourquoi
    0.06
    bilt
    0.06
    plements
    0.06
    _AUT
    0.06
     Republican
    0.06
    ازات
    0.06
    Activations Density 0.003%

    No Known Activations