© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126621
    Prev
    Next
    INDEX
    Explanations

    definitions/descriptions

    np_max-act · gemini-2.0-flash

    The neuron fires on the token “description,” i.e. when the user mentions “description” in their request.

    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
    =out
    -0.07
    layarak
    -0.07
    _MAP
    -0.06
    호
    -0.06
    》的
    -0.06
    _RESET
    -0.06
     взгляд
    -0.06
     eg
    -0.06
    کور
    -0.06
     perfume
    -0.06
    POSITIVE LOGITS
     terribly
    0.06
    (@
    0.06
     peel
    0.06
    tatus
    0.06
     Spir
    0.06
     Exhibit
    0.06
     Bans
    0.06
    ...↵↵
    0.06
    Repositories
    0.06
     showcase
    0.06
    Activations Density 0.002%

    No Known Activations