© 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. 6529
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron fires on structural/control tokens used in the JSON-like or special markup (e.g. `<|…|>`, braces, quotes, colons), i.e. it identifies the formatting delimiters rather than content words.

    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
    _tag
    -0.07
    spe
    -0.07
    벌
    -0.06
    enty
    -0.06
    .ne
    -0.06
     imgs
    -0.06
    _types
    -0.06
     GAME
    -0.06
    賢
    -0.06
    classmethod
    -0.06
    POSITIVE LOGITS
    ]*
    0.07
     designed
    0.07
    @Web
    0.06
     [])↵↵
    0.06
     Ashley
    0.06
     '')↵
    0.06
     nood
    0.06
     injecting
    0.06
    :=
    0.06
     *
    0.06
    Activations Density 0.005%

    No Known Activations