© 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. 40939
    Prev
    Next
    INDEX
    Explanations

    command line

    np_max-act · gemini-2.0-flash

    This neuron fires on shell‐style prompt and command‐invocation tokens (e.g. “$”, “sudo”, host/user prompts, colons in CLI contexts).

    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
    Unfortunately
    -0.06
     Cards
    -0.06
     IX
    -0.06
     Num
    -0.06
    Asc
    -0.06
    xdb
    -0.06
     Над
    -0.06
    DATA
    -0.06
    uelles
    -0.06
     lov
    -0.06
    POSITIVE LOGITS
     aplik
    0.07
    .CH
    0.07
    _mov
    0.06
    .DropDown
    0.06
    _COUNTER
    0.06
    _hat
    0.06
    ulumi
    0.06
    topic
    0.06
     argued
    0.06
     strtoupper
    0.06
    Activations Density 0.035%

    No Known Activations