© 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. 29424
    Prev
    Next
    INDEX
    Explanations

    work

    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
     output
    -0.07
     dahil
    -0.07
     dose
    -0.06
    ssel
    -0.06
     Besch
    -0.06
    ’autres
    -0.06
    conditions
    -0.06
     heading
    -0.06
    _accuracy
    -0.06
    出现
    -0.06
    POSITIVE LOGITS
     život
    0.07
     PSU
    0.06
    {i
    0.06
     yaşam
    0.06
     Malaysian
    0.06
    *@
    0.06
    -val
    0.06
    \"",
    0.06
     twin
    0.06
     mainland
    0.06
    Activations Density 0.000%

    No Known Activations