© 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. 7-RESID-POST-AA
    6. 46555
    Prev
    Next
    INDEX
    Explanations

    :

    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
     PRICE
    -0.07
     Recently
    -0.07
    ה
    -0.07
    Ô
    -0.07
     factorial
    -0.07
    翰
    -0.06
     Simpl
    -0.06
    mathrm
    -0.06
     ly
    -0.06
    pow
    -0.06
    POSITIVE LOGITS
    __(↵
    0.07
    .GroupLayout
    0.07
    oscope
    0.06
     хотя
    0.06
     otur
    0.06
    خر
    0.06
    益
    0.06
     dầu
    0.06
    Moon
    0.06
     VN
    0.06
    Activations Density 0.039%

    No Known Activations