© 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. 78105
    Prev
    Next
    INDEX
    Explanations

    pressure

    np_max-act · gemini-2.0-flash

    technical terminology and details related to the design and function of pressure sensors in semiconductor applications.

    oai_token-act-pair · gpt-4o-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
    891
    -0.06
    rogen
    -0.06
    bel
    -0.06
    вин
    -0.06
    IDEOS
    -0.06
    errupted
    -0.06
     json
    -0.06
    norm
    -0.06
     Quit
    -0.06
    letes
    -0.05
    POSITIVE LOGITS
     airs
    0.07
     visuals
    0.07
     zprac
    0.06
     rua
    0.06
     chiff
    0.06
     laat
    0.06
    _strength
    0.06
    .reshape
    0.06
     způsobem
    0.06
    你的
    0.06
    Activations Density 0.029%

    No Known Activations