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. 87062
    Prev
    Next
    INDEX
    Explanations

    seek

    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
    وپ
    -0.07
     Sc
    -0.07
    Heap
    -0.07
    倫
    -0.06
    fft
    -0.06
    OfType
    -0.06
    Ptr
    -0.06
     ');↵
    -0.06
     IList
    -0.06
    со
    -0.06
    POSITIVE LOGITS
     jdbcTemplate
    0.07
     thanh
    0.06
     Fortunately
    0.06
     появ
    0.06
    _Save
    0.06
     immigration
    0.06
     Aeros
    0.06
     возв
    0.06
     extrapol
    0.06
    �
    0.06
    Activations Density 0.018%

    No Known Activations