© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93952
    Prev
    Next
    INDEX
    Explanations

    dialysis

    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
     dijo
    -0.07
    .keyword
    -0.07
    placing
    -0.06
     lorem
    -0.06
     fade
    -0.06
     punishment
    -0.06
     orientations
    -0.06
    [arg
    -0.06
    ف
    -0.06
     whereby
    -0.06
    POSITIVE LOGITS
    odial
    0.20
     До
    0.07
     glitter
    0.06
    ंधन
    0.06
    _phys
    0.06
    节
    0.06
     Belly
    0.06
     AUD
    0.06
    kovi
    0.06
    ΥΝ
    0.06
    Activations Density 0.002%

    No Known Activations