© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9159
    Prev
    Next
    INDEX
    Explanations

    automatically

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dir
    -0.07
    луж
    -0.06
     guy
    -0.06
    orpor
    -0.06
    Extensions
    -0.06
    IEWS
    -0.06
    ulist
    -0.06
    illustr
    -0.06
     tantr
    -0.06
    neas
    -0.06
    POSITIVE LOGITS
     automatically
    0.07
    !」
    0.07
    879
    0.07
    stvo
    0.07
     Nie
    0.07
    .EventHandler
    0.06
     cholesterol
    0.06
    _LONG
    0.06
    链
    0.06
     autop
    0.06
    Activations Density 0.015%

    No Known Activations