© 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. 7-RESID-POST-AA
    11. 31640
    Prev
    Next
    INDEX
    Explanations

    chemical/chemicals

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Global
    -0.07
     burned
    -0.06
     access
    -0.06
    Envelope
    -0.06
    切り
    -0.06
    Path
    -0.06
     Luft
    -0.06
     gains
    -0.06
    _RUNTIME
    -0.06
     buttons
    -0.06
    POSITIVE LOGITS
     завер
    0.06
     Facts
    0.06
    ــ
    0.06
    :>
    0.06
     enumerate
    0.06
     discovers
    0.06
    /The
    0.06
     nutrient
    0.06
    lene
    0.06
     accustomed
    0.06
    Activations Density 0.026%

    No Known Activations