Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88647
    Prev
    Next
    INDEX
    Explanations

    legal cases

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    infos
    -0.07
     оці
    -0.07
    tě
    -0.06
    Even
    -0.06
    Jeff
    -0.06
    Minus
    -0.06
    Neg
    -0.06
     Retry
    -0.06
    HttpStatus
    -0.06
     selectedItem
    -0.06
    POSITIVE LOGITS
     klub
    0.07
    刊
    0.07
    _Generic
    0.06
     терап
    0.06
     Paramount
    0.06
     arresting
    0.06
    marginTop
    0.06
     discovering
    0.06
    _INTER
    0.06
     trẻ
    0.06
    Activations Density 0.008%

    No Known Activations