© 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. 45995
    Prev
    Next
    INDEX
    Explanations

    to

    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
    dex
    -0.08
    鄉
    -0.07
    用户名
    -0.06
     Sew
    -0.06
    Talk
    -0.06
    傷
    -0.06
    innamon
    -0.06
    	reg
    -0.06
    erot
    -0.06
    ámara
    -0.06
    POSITIVE LOGITS
     aValue
    0.07
    .utf
    0.06
    ctrine
    0.06
    CriticalSection
    0.06
     flask
    0.06
    .collider
    0.06
     tensorflow
    0.06
     Comparator
    0.06
     rozhod
    0.06
     кроме
    0.06
    Activations Density 0.302%

    No Known Activations