© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121860
    Prev
    Next
    INDEX
    Explanations

    backtick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blade
    -0.06
    abancı
    -0.06
    ss
    -0.06
     Avatar
    -0.06
    (tool
    -0.06
    PLIER
    -0.06
     brushed
    -0.06
    ัค
    -0.06
    EDIUM
    -0.06
     chromosomes
    -0.06
    POSITIVE LOGITS
    .showMessageDialog
    0.08
    :value
    0.08
     coun
    0.07
     `,↵
    0.07
     brit
    0.06
     cartridges
    0.06
    .attachment
    0.06
    parms
    0.06
     Δημο
    0.06
    .getTarget
    0.06
    Activations Density 0.010%

    No Known Activations