© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 76183
    Prev
    Next
    INDEX
    Explanations

    risk

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Compute
    -0.07
     write
    -0.07
    (add
    -0.07
     значения
    -0.07
     inout
    -0.06
    ываем
    -0.06
     writes
    -0.06
    _edit
    -0.06
    -0.06
    printing
    -0.06
    POSITIVE LOGITS
     Risk
    0.06
     Bay
    0.06
    μει
    0.06
     самый
    0.06
    ehicles
    0.06
     Sodium
    0.06
    Bay
    0.06
    ationale
    0.06
     Sunshine
    0.06
    egasus
    0.06
    Activations Density 0.005%

    No Known Activations