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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 1170
    Prev
    Next
    INDEX
    Explanations

    business accreditations

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of quality management and ISO certification terminology (e.g., “ISO 9001:2015,” “quality management,” “commitment to quality”).

    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
     therm
    -0.07
    (user
    -0.07
     V
    -0.07
    یه
    -0.06
    749
    -0.06
     GL
    -0.06
     playoffs
    -0.06
     dever
    -0.06
     turbo
    -0.06
     DAMAGES
    -0.06
    POSITIVE LOGITS
     %+
    0.08
    Usually
    0.07
    FFECT
    0.06
    getStatusCode
    0.06
    ']);↵
    0.06
    velopment
    0.06
     зрения
    0.06
    ORM
    0.06
    .setMax
    0.06
     vbCrLf
    0.06
    Activations Density 0.015%

    No Known Activations