© 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. 7-RESID-POST-AA
    11. 108656
    Prev
    Next
    INDEX
    Explanations

    into

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trent
    -0.08
     uncomfort
    -0.06
     Volley
    -0.06
    vek
    -0.06
    cred
    -0.06
    .un
    -0.06
    �
    -0.06
    �
    -0.06
     organs
    -0.06
     trans
    -0.06
    POSITIVE LOGITS
    Perfil
    0.08
     Datensch
    0.07
    _PROC
    0.07
     voluntarily
    0.07
    .QLabel
    0.06
    BOSE
    0.06
     into
    0.06
    YA
    0.06
    Angular
    0.06
    ActionTypes
    0.06
    Activations Density 0.011%

    No Known Activations