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

    Neuronpedia

    Jacobian LensNEW
    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. 38307
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron fires on technical action verbs describing what a device or component does (e.g. “driving,” “producing,” “exciting,” “reflecting,” “allowing”).

    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
     douche
    -0.07
     tau
    -0.07
    Tau
    -0.06
     刘
    -0.06
    CurrentUser
    -0.06
     combineReducers
    -0.06
     　　　　
    -0.06
    .targets
    -0.06
    ContainerGap
    -0.06
     viewPager
    -0.06
    POSITIVE LOGITS
    BF
    0.07
     FOR
    0.07
    (time
    0.07
     Springfield
    0.07
    4
    0.07
     http
    0.07
    FOR
    0.07
     Pick
    0.07
     Tiles
    0.07
    For
    0.06
    Activations Density 0.017%

    No Known Activations