© 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. 29453
    Prev
    Next
    INDEX
    Explanations

    .Chrome

    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
     Seal
    -0.08
    вается
    -0.06
    寻
    -0.06
    softmax
    -0.06
    чист
    -0.06
     تخصصی
    -0.06
    젠
    -0.06
     Kiş
    -0.06
    segue
    -0.06
    bias
    -0.06
    POSITIVE LOGITS
     occupations
    0.07
     mechanisms
    0.07
     Numeric
    0.07
    OM
    0.07
     mechanism
    0.07
    armac
    0.06
     لی
    0.06
     PD
    0.06
    .numberOfLines
    0.06
    =Math
    0.06
    Activations Density 0.011%

    No Known Activations