© 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. 21291
    Prev
    Next
    INDEX
    Explanations

    period

    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
     동
    -0.07
    Couldn
    -0.07
     capital
    -0.07
     ero
    -0.07
    kir
    -0.06
    fl
    -0.06
    	open
    -0.06
     epis
    -0.06
    hyth
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     unload
    0.06
    Maintenance
    0.06
    columnName
    0.06
     Down
    0.06
    /sc
    0.06
     Dimension
    0.06
    ).</
    0.06
     Hurricane
    0.06
    LOPT
    0.06
     SHARE
    0.06
    Activations Density 0.018%

    No Known Activations