© 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. 3-RESID-POST-AA
    6. 123045
    Prev
    Next
    INDEX
    Explanations

    Teams and players

    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
     presumably
    -0.06
     faux
    -0.06
     COM
    -0.06
     nepří
    -0.05
     औ
    -0.05
     trophy
    -0.05
     prosec
    -0.05
     imp
    -0.05
     murdering
    -0.05
    >y
    -0.05
    POSITIVE LOGITS
     diagrams
    0.08
    ший
    0.07
    ESIS
    0.07
     лицо
    0.07
    (answer
    0.06
    clerosis
    0.06
    ロン
    0.06
    vrier
    0.06
     tải
    0.06
    AFE
    0.06
    Activations Density 0.006%

    No Known Activations