© 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. 91434
    Prev
    Next
    INDEX
    Explanations

    study

    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
    IBLE
    -0.07
     лишь
    -0.07
    ancers
    -0.07
    thren
    -0.07
     pursue
    -0.07
    umes
    -0.07
     گ
    -0.07
    checks
    -0.06
    錢
    -0.06
     когда
    -0.06
    POSITIVE LOGITS
     searchTerm
    0.07
     obnov
    0.06
     serialize
    0.06
    .ibm
    0.06
     Ngb
    0.06
    odon
    0.05
     downt
    0.05
    (plot
    0.05
     onSuccess
    0.05
    Expired
    0.05
    Activations Density 0.023%

    No Known Activations