© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44393
    Prev
    Next
    INDEX
    Explanations

    components or ingredients

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of substances and process inputs—words like “chemicals,” “reagents,” “ingredients,” and “mixing.”

    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
    カル
    -0.07
     Hampton
    -0.06
    .form
    -0.06
    แนะ
    -0.06
    fe
    -0.06
    compareTo
    -0.06
     volatile
    -0.05
     watchers
    -0.05
    callback
    -0.05
    /User
    -0.05
    POSITIVE LOGITS
    380
    0.07
     Gina
    0.06
     Urb
    0.06
    final
    0.06
    _DIST
    0.06
    Authenticated
    0.06
    _temp
    0.06
    PEED
    0.06
    ############################
    0.06
    _attachment
    0.06
    Activations Density 0.015%

    No Known Activations