Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93459
    Prev
    Next
    INDEX
    Explanations

    line

    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
     myths
    -0.07
    =g
    -0.06
    [o
    -0.06
    (pd
    -0.06
     ممکن
    -0.06
     trao
    -0.06
    &utm
    -0.06
    rats
    -0.06
     Zi
    -0.06
    T
    -0.06
    POSITIVE LOGITS
     شود
    0.07
     syrup
    0.06
     wearable
    0.06
    REFERENCES
    0.06
    limits
    0.06
    winter
    0.06
    най
    0.06
     lug
    0.06
     murderer
    0.06
    /history
    0.06
    Activations Density 0.001%

    No Known Activations