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. 130592
    Prev
    Next
    INDEX
    Explanations

    result

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on common function words and abstract relational terms (e.g. prepositions, conjunctions, and other “stop” words).

    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
     setUsername
    -0.07
    	D
    -0.07
    TestMethod
    -0.07
     Disconnect
    -0.07
    -form
    -0.07
    (clone
    -0.06
     going
    -0.06
     recogn
    -0.06
    ("[
    -0.06
    青年
    -0.06
    POSITIVE LOGITS
    ysl
    0.08
    estado
    0.07
    ikers
    0.06
    iena
    0.06
    esar
    0.06
    .Canvas
    0.06
    iva
    0.06
    annya
    0.06
     Georges
    0.06
    bitset
    0.06
    Activations Density 0.280%

    No Known Activations