© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 40788
    Prev
    Next
    INDEX
    Explanations

    295

    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
    ADIUS
    -0.07
     Son
    -0.07
    ategory
    -0.07
    .Rad
    -0.07
     onion
    -0.07
     eid
    -0.07
     السعود
    -0.07
     zombie
    -0.07
     substitution
    -0.07
     Sing
    -0.07
    POSITIVE LOGITS
    797
    0.09
    396
    0.09
    593
    0.09
    293
    0.09
    790
    0.08
    392
    0.08
    590
    0.08
    693
    0.08
    297
    0.08
    494
    0.08
    Activations Density 0.080%

    No Known Activations