© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 9016
    Prev
    Next
    INDEX
    Explanations

    colorimetric assays

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the term “colorimetric,” i.e. references to colorimetric assays or measurements.

    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
    _By
    -0.08
     ConfigureServices
    -0.07
    ادا
    -0.07
     welded
    -0.07
    ]init
    -0.06
     SOLD
    -0.06
    His
    -0.06
     msg
    -0.06
     Exec
    -0.06
    _frac
    -0.06
    POSITIVE LOGITS
     kits
    0.06
     deton
    0.06
    缘
    0.06
    orient
    0.06
     �
    0.06
    iž
    0.06
    _elim
    0.06
    fer
    0.06
     carb
    0.06
    erah
    0.05
    Activations Density 0.001%

    No Known Activations