© 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. 19-RESID-POST-AA
    11. 54547
    Prev
    Next
    INDEX
    Explanations

    cultured

    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
     разі
    -0.07
    isers
    -0.07
    .JScrollPane
    -0.07
     更新
    -0.07
    _mp
    -0.06
     DATA
    -0.06
    шив
    -0.06
     {}.
    -0.06
    licas
    -0.06
    _stats
    -0.06
    POSITIVE LOGITS
    .isTrue
    0.06
     bool
    0.06
     hf
    0.06
     hin
    0.06
     że
    0.06
     Atom
    0.06
    ?s
    0.06
    {{$
    0.06
     TOO
    0.06
     gee
    0.06
    Activations Density 0.060%

    No Known Activations