© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 87784
    Prev
    Next
    INDEX
    Explanations

    harm or loss

    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
    ρευ
    -0.06
    ерк
    -0.06
     NPCs
    -0.06
    ativní
    -0.06
    /cards
    -0.06
     userDetails
    -0.06
     headquartered
    -0.06
     Objects
    -0.06
    _impl
    -0.06
    .Information
    -0.06
    POSITIVE LOGITS
     deform
    0.07
     arous
    0.06
    Impact
    0.06
     agitation
    0.06
     Morrow
    0.06
     Yale
    0.06
     определ
    0.06
     κ
    0.06
    {$
    0.06
     fifty
    0.06
    Activations Density 0.012%

    No Known Activations