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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 87042
    Prev
    Next
    INDEX
    Explanations

    References

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _StaticFields
    -0.07
     Fault
    -0.07
     hamm
    -0.07
    _dicts
    -0.06
     -*-
    ↵
    -0.06
    木
    -0.06
    -bg
    -0.06
    _avatar
    -0.06
    jà
    -0.06
    ustom
    -0.06
    POSITIVE LOGITS
    кие
    0.07
    .link
    0.06
    tips
    0.06
     lips
    0.06
     eradicate
    0.06
     Unblock
    0.06
     Being
    0.06
     sorter
    0.06
    okableCall
    0.06
     With
    0.06
    Activations Density 0.018%

    No Known Activations