© 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
    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. 54358
    Prev
    Next
    INDEX
    Explanations

    role

    np_max-act · gemini-2.0-flash

    references to physiological studies related to cellular impacts and conditions.

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

    This neuron detects the causal-speculation phrase “play a role in.”

    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
     D
    -0.07
     movies
    -0.07
     RD
    -0.07
     Po
    -0.07
     policies
    -0.07
     HPV
    -0.06
    umbn
    -0.06
    (P
    -0.06
     illusion
    -0.06
     hạng
    -0.06
    POSITIVE LOGITS
    rtle
    0.07
    icester
    0.07
     "\">
    0.06
    ذي
    0.06
    .setIcon
    0.06
     realidad
    0.06
     &&
↵
    0.06
     Sniper
    0.06
    '],↵↵
    0.06
    CTYPE
    0.06
    Activations Density 0.030%

    No Known Activations