© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7934
    Prev
    Next
    INDEX
    Explanations

    versions or edition numbers

    np_max-act · gemini-2.0-flash

    The neuron detects tokens involved in asking or stating the model’s GPT version (e.g. “GPT-4,” “version,” “running on,” “g,” “pt,” “-,” digits).

    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
     gated
    -0.06
    Ｌ
    -0.06
    icon
    -0.06
    ロ
    -0.06
    ino
    -0.06
    倫
    -0.06
     messageId
    -0.06
    _mix
    -0.06
    یز
    -0.06
    払
    -0.06
    POSITIVE LOGITS
    ,model
    0.07
    	setTimeout
    0.07
     Evelyn
    0.07
    bury
    0.06
     Occup
    0.06
     blossom
    0.06
     ro
    0.06
    -BEGIN
    0.06
    -compose
    0.06
     accompanying
    0.06
    Activations Density 0.027%

    No Known Activations