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. 19-RESID-POST-AA
    6. 31532
    Prev
    Next
    INDEX
    Explanations

    countering claims with evidence

    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
     ─
    -0.07
    ını
    -0.07
    esty
    -0.06
    edriver
    -0.06
    ocities
    -0.06
    TreeView
    -0.06
     Crisis
    -0.06
     在
    -0.06
     notre
    -0.06
     więcej
    -0.06
    POSITIVE LOGITS
     дир
    0.07
     adjust
    0.07
    \system
    0.06
    (PATH
    0.06
     ตำบล
    0.06
    bum
    0.06
    _keep
    0.06
     hills
    0.06
     deactivate
    0.06
     خاک
    0.06
    Activations Density 0.075%

    No Known Activations