© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43045
    Prev
    Next
    INDEX
    Explanations

    industrial

    np_max-act · gemini-2.0-flash

    chemical compounds and their production processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires strongly on mentions of the “chemical industry” domain—particularly the tokens “chemical” and “industry” (often with “the” immediately before).

    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
     `\
    -0.07
    ゲーム
    -0.06
     }]↵
    -0.06
     ascending
    -0.06
     carriage
    -0.06
    reward
    -0.06
     usa
    -0.06
    ,↵↵↵↵
    -0.06
     wood
    -0.06
    (...)↵
    -0.06
    POSITIVE LOGITS
    tığ
    0.06
     pledged
    0.06
    (varargin
    0.06
    ICON
    0.06
    DR
    0.06
    Separator
    0.06
    Billing
    0.06
     olab
    0.06
    三三
    0.05
    CTYPE
    0.05
    Activations Density 0.022%

    No Known Activations