© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 109388
    Prev
    Next
    INDEX
    Explanations

    Quotation marks/names

    np_max-act · gemini-2.0-flash

    references to historical or cultural events and figures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects the main proper‐noun title tokens at the start of a section or article (i.e. the headline or primary name).

    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
     objections
    -0.06
    ENDER
    -0.06
     eBooks
    -0.06
     Fine
    -0.06
    COUNT
    -0.06
     QUERY
    -0.06
     AUTH
    -0.06
    ,column
    -0.06
    олж
    -0.06
     abych
    -0.06
    POSITIVE LOGITS
    $/,
    0.07
    =$((
    0.07
     mascot
    0.06
    }};↵
    0.06
    .material
    0.06
    -rad
    0.06
    <?=$
    0.06
    /json
    0.06
     referendum
    0.06
     THEY
    0.06
    Activations Density 0.058%

    No Known Activations