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. 86060
    Prev
    Next
    INDEX
    Explanations

    References and external links

    np_max-act · gemini-2.0-flash

    The neuron is triggered by Wikipedia category markers (the “Category:” labels at the end of articles).

    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
    Dict
    -0.07
    	vertices
    -0.07
     avez
    -0.06
    onest
    -0.06
     wszyst
    -0.06
     zač
    -0.06
    /DD
    -0.06
     Repeat
    -0.06
    훈
    -0.06
    ignet
    -0.06
    POSITIVE LOGITS
    ──
    0.07
    owej
    0.06
     đến
    0.06
                                                                               
    0.06
     bele
    0.06
     (/
    0.06
     sedan
    0.06
     основных
    0.06
     TAS
    0.06
    _kb
    0.06
    Activations Density 0.010%

    No Known Activations