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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3-RESID-POST-AA
    6. 122033
    Prev
    Next
    INDEX
    Explanations

    ause

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zack
    -0.07
    .loc
    -0.06
     شامل
    -0.06
    ibName
    -0.06
     municipalities
    -0.06
     talks
    -0.06
    <long
    -0.06
     durch
    -0.06
    Li
    -0.06
     объем
    -0.06
    POSITIVE LOGITS
    Pause
    0.16
    .paused
    0.15
    .pause
    0.14
    pause
    0.13
    _PAUSE
    0.13
    paused
    0.12
    Paused
    0.11
    ause
    0.10
     Pause
    0.10
     onPause
    0.10
    Activations Density 0.006%

    No Known Activations