© 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. 89785
    Prev
    Next
    INDEX
    Explanations

    injury

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of legal compensation or harm quantification (e.g. damages, losses, injury).

    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
    .EventArgs
    -0.07
    tester
    -0.07
    _TEM
    -0.06
     txn
    -0.06
     Initializing
    -0.06
    _called
    -0.06
     Operand
    -0.06
    .Roll
    -0.06
     Analytics
    -0.06
     Tone
    -0.06
    POSITIVE LOGITS
     Ν
    0.07
     obstruct
    0.07
    -country
    0.07
     offerings
    0.07
    /sub
    0.07
    .travel
    0.07
     поверхности
    0.06
    ์กร
    0.06
    universal
    0.06
    BOARD
    0.06
    Activations Density 0.012%

    No Known Activations