© 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. 75561
    Prev
    Next
    INDEX
    Explanations

    about

    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
     piles
    -0.06
     tấm
    -0.06
     vowel
    -0.06
     пал
    -0.06
    iPad
    -0.06
    cdecl
    -0.06
    };
    ↵
    -0.06
    高い
    -0.06
     kind
    -0.06
    _PUS
    -0.06
    POSITIVE LOGITS
     about
    0.12
    about
    0.11
    -about
    0.07
     About
    0.07
     NH
    0.07
     ABOUT
    0.07
     etwa
    0.07
    around
    0.07
     Saunders
    0.07
    abouts
    0.07
    Activations Density 0.009%

    No Known Activations