© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125207
    Prev
    Next
    INDEX
    Explanations

    Studies

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of academic or professional titles and fields of study (e.g., discipline names and roles).

    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
    motor
    -0.07
     몸을
    -0.07
     Ish
    -0.07
     frække
    -0.06
    =DB
    -0.06
    weighted
    -0.06
    ERC
    -0.06
     wxT
    -0.06
    cookies
    -0.06
    brook
    -0.06
    POSITIVE LOGITS
    ufe
    0.07
    '][$
    0.06
    _HOLD
    0.06
     compliance
    0.06
     sovereignty
    0.06
     Landing
    0.06
    ucht
    0.06
     Severity
    0.06
     secrecy
    0.06
    _sched
    0.06
    Activations Density 0.029%

    No Known Activations