© 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. 127104
    Prev
    Next
    INDEX
    Explanations

    prove

    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
    มาก
    -0.07
    Taken
    -0.07
     WM
    -0.06
    包
    -0.06
    ้าร
    -0.06
     ورزشی
    -0.06
     Taken
    -0.06
     Doming
    -0.06
    _FRE
    -0.06
    гів
    -0.06
    POSITIVE LOGITS
     proved
    0.07
    isclosed
    0.07
     scores
    0.07
     score
    0.07
    绩
    0.06
    iedo
    0.06
     Same
    0.06
     predicts
    0.06
     archivo
    0.06
     порів
    0.06
    Activations Density 0.010%

    No Known Activations