Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55690
    Prev
    Next
    INDEX
    Explanations

    complaint

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “complaint” (and its morphological variants) in legal filings.

    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
    ันว
    -0.07
     англ
    -0.07
     Jordan
    -0.06
     Hugo
    -0.06
     Il
    -0.06
    Mit
    -0.06
    etal
    -0.06
    (team
    -0.06
     talks
    -0.06
     student
    -0.06
    POSITIVE LOGITS
     √
    0.08
     safezone
    0.07
     misdemean
    0.06
     của
    0.06
    vio
    0.06
     đẹp
    0.06
    ClearColor
    0.06
    phant
    0.06
    usahaan
    0.06
     BusinessException
    0.06
    Activations Density 0.004%

    No Known Activations