© 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. 3-RESID-POST-AA
    11. 121928
    Prev
    Next
    INDEX
    Explanations

    open

    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
    Thunk
    -0.07
    成绩
    -0.06
    (cli
    -0.06
     Persona
    -0.06
    .Preference
    -0.06
    ?=
    -0.06
    -gr
    -0.06
    Δεν
    -0.06
    ()).
    -0.06
    转
    -0.06
    POSITIVE LOGITS
    _open
    0.09
    .Close
    0.08
     open
    0.08
     clips
    0.07
     widget
    0.07
     boosting
    0.06
    bau
    0.06
     vital
    0.06
     문의
    0.06
     gốc
    0.06
    Activations Density 0.023%

    No Known Activations