© 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. 99601
    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
    ену
    -0.07
    �
    -0.06
    loating
    -0.06
     dow
    -0.06
    hyp
    -0.06
    -strong
    -0.06
     PID
    -0.06
     karış
    -0.06
     weighs
    -0.06
    _TYPES
    -0.06
    POSITIVE LOGITS
    식
    0.07
     CL
    0.07
    (OpCodes
    0.06
    .coord
    0.06
     Snow
    0.06
    ’i
    0.06
    'i
    0.06
     Unsafe
    0.06
     реєстра
    0.06
    .paper
    0.06
    Activations Density 0.090%

    No Known Activations