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. 130631
    Prev
    Next
    INDEX
    Explanations

    method overriding

    np_max-act · gemini-2.0-flash

    This neuron fires on code tokens that declare or override methods (e.g. the “override” keyword, return type and method name patterns like “void draw()”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <data
    -0.07
     www
    -0.06
     disabling
    -0.06
     fait
    -0.06
     desk
    -0.06
    	pstmt
    -0.06
    	fflush
    -0.06
    _saved
    -0.06
    .surface
    -0.06
     clave
    -0.06
    POSITIVE LOGITS
    -needed
    0.07
    (dy
    0.07
     ця
    0.06
    ]));
    ↵
    0.06
    ibbon
    0.06
     discovery
    0.06
    .Ok
    0.06
     url
    0.06
     birey
    0.06
     PdfPCell
    0.06
    Activations Density 0.016%

    No Known Activations