© 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. 91067
    Prev
    Next
    INDEX
    Explanations

    manufacturers

    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
    .mousePosition
    -0.08
    かし
    -0.08
    	game
    -0.07
    _relu
    -0.07
     haut
    -0.07
    .radians
    -0.07
    ďte
    -0.06
    .(*
    -0.06
    _FRIEND
    -0.06
    .fetchone
    -0.06
    POSITIVE LOGITS
    _lib
    0.07
    成功
    0.07
     địa
    0.07
     ein
    0.06
    电
    0.06
    nr
    0.06
     contradictions
    0.06
    Further
    0.06
    星
    0.06
    Basic
    0.06
    Activations Density 0.022%

    No Known Activations