© 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. 125090
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron detects document headings or section titles, especially lines ending with a colon (often including years or topic labels).

    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
    Ted
    -0.07
     contemporary
    -0.07
     misunderstanding
    -0.07
     kidding
    -0.06
     такими
    -0.06
     palabras
    -0.06
    ьер
    -0.06
    -faced
    -0.06
    /U
    -0.06
    ASTER
    -0.06
    POSITIVE LOGITS
    :
    0.09
    :↵
    0.07
     :
    0.07
     overs
    0.07
    ):
    0.06
    /random
    0.06
    :g
    0.06
    "):
    ↵
    0.06
     投
    0.06
    (toolbar
    0.06
    Activations Density 0.043%

    No Known Activations