© 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. 128788
    Prev
    Next
    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash

    The neuron detects degree-modifier words—intensifying adverbs and similar qualifiers (e.g. “mere,” “simply,” “solely,” “just”) that emphasize or scale an action or description.

    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
    .Xml
    -0.07
    ึ
    -0.07
     Olive
    -0.06
     barrage
    -0.06
     nau
    -0.06
     reput
    -0.06
     Warriors
    -0.06
    roman
    -0.06
     anytime
    -0.06
    耐
    -0.06
    POSITIVE LOGITS
     Named
    0.07
    _action
    0.06
    _At
    0.06
    provider
    0.06
     indictment
    0.06
    ',...↵
    0.06
    _series
    0.06
    Shader
    0.06
     пев
    0.06
     destin
    0.06
    Activations Density 0.067%

    No Known Activations