© 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. 59357
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron detects entity-attribution labels, i.e. proper names or sources followed by a colon (e.g. “Haley:”, “Verizon:”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    #af
    -0.07
    、私
    -0.06
    #ab
    -0.06
     혼
    -0.06
     defin
    -0.06
    ука
    -0.06
    ук
    -0.05
    _RETURN
    -0.05
    ovanou
    -0.05
    .MATCH
    -0.05
    POSITIVE LOGITS
    trieve
    0.09
    نسية
    0.07
    :
    0.07
    pción
    0.07
     следует
    0.07
     tượng
    0.07
     investigación
    0.07
    ails
    0.07
    iggers
    0.07
     GN
    0.07
    Activations Density 0.009%

    No Known Activations