© 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. 125965
    Prev
    Next
    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash

    This neuron detects negative or prohibitive cue words (e.g. “not,” “never,” “don’t,” “may not”) used to signal prohibition or caution.

    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
    Grid
    -0.06
    sequent
    -0.06
    cb
    -0.06
    etrize
    -0.06
    regexp
    -0.06
    _characters
    -0.06
     Presence
    -0.06
    getMethod
    -0.06
    RelativeLayout
    -0.06
    ศร
    -0.06
    POSITIVE LOGITS
    >this
    0.06
     Mega
    0.06
    전히
    0.06
     enam
    0.06
     redistribute
    0.06
    .getD
    0.06
    .pipe
    0.06
     awful
    0.06
    ught
    0.06
    ΩΣ
    0.06
    Activations Density 0.041%

    No Known Activations