© 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. 41631
    Prev
    Next
    INDEX
    Explanations

    asses

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting warning-type language—phrases and metaphors that signal danger or serve as early alerts.

    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
    ableOpacity
    -0.08
     hormonal
    -0.07
    currentTime
    -0.06
    _listener
    -0.06
    Rectangle
    -0.06
    เต
    -0.06
    이며
    -0.06
    沉
    -0.06
     رز
    -0.06
     addCriterion
    -0.06
    POSITIVE LOGITS
    _join
    0.07
    -kit
    0.06
    hk
    0.06
    πλα
    0.06
    (width
    0.06
    찌
    0.06
    уватися
    0.06
    èles
    0.06
    phinx
    0.06
     notre
    0.06
    Activations Density 0.074%

    No Known Activations