© 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. 30064
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on technical identifier tokens—e.g. function or configuration directive names (like “sets.New.String”, “AllowUsers”, “v=spf1”).

    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
    cen
    -0.06
    )const
    -0.06
    yk
    -0.06
     },{
    -0.06
    ","+
    -0.06
    )[
    -0.06
    ],↵
    -0.06
     charset
    -0.06
    ています
    -0.06
    /node
    -0.06
    POSITIVE LOGITS
     autre
    0.08
    atonin
    0.07
    ρε
    0.07
    ografia
    0.07
     existence
    0.06
     restaurant
    0.06
    ';↵↵↵↵
    0.06
    争
    0.06
     indulge
    0.06
     pleasant
    0.06
    Activations Density 0.077%

    No Known Activations