© 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. 31784
    Prev
    Next
    INDEX
    Explanations

    :

    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
     Southern
    -0.07
    ibar
    -0.07
    _AR
    -0.07
     �
    -0.07
    -l
    -0.07
    ibraries
    -0.07
    ヤ
    -0.07
    -real
    -0.06
     mulheres
    -0.06
    imax
    -0.06
    POSITIVE LOGITS
     Skip
    0.07
     probing
    0.06
     Except
    0.06
     defaulted
    0.06
    Reducer
    0.06
     départ
    0.06
    这样
    0.06
     انتظ
    0.06
     theft
    0.06
     civilizations
    0.06
    Activations Density 0.009%

    No Known Activations