© 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. 9788
    Prev
    Next
    INDEX
    Explanations

    rom

    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
     pepper
    -0.07
     Everywhere
    -0.07
    ice
    -0.06
     sona
    -0.06
     Keynes
    -0.06
     converge
    -0.06
    _fps
    -0.06
     фрон
    -0.06
     pais
    -0.06
    xxxx
    -0.06
    POSITIVE LOGITS
    <std
    0.07
     throm
    0.07
    rom
    0.06
    <|start_header_id|>
    0.06
    oglob
    0.06
    ategorical
    0.06
    chrono
    0.06
    morgan
    0.06
    絶
    0.06
     र
    0.06
    Activations Density 0.000%

    No Known Activations