© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 118275
    Prev
    Next
    INDEX
    Explanations

    which

    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
    よう
    -0.06
     tienen
    -0.06
     достав
    -0.06
    gesch
    -0.06
     goalie
    -0.06
    そう
    -0.06
    olini
    -0.06
     máme
    -0.05
    lo
    -0.05
     yaptık
    -0.05
    POSITIVE LOGITS
    _transition
    0.07
     ฟ
    0.07
     Taş
    0.07
    _AC
    0.07
    -makers
    0.07
    .ToString
    0.07
    _input
    0.06
    .middle
    0.06
     PROJECT
    0.06
    腐
    0.06
    Activations Density 0.206%

    No Known Activations