© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 124992
    Prev
    Next
    INDEX
    Explanations

    Go packages

    np_max-act · gemini-2.0-flash

    The neuron spots Go import‐path identifiers—that is, library/package names in import statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code structures and functions related to API endpoints and resource management.

    oai_token-act-pair · gpt-4o-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
     esteem
    -0.06
     yếu
    -0.06
    чі
    -0.06
     “
    -0.06
     безпеки
    -0.06
    ))){↵
    -0.06
    >>&
    -0.05
    gewater
    -0.05
    );">↵
    -0.05
    이라고
    -0.05
    POSITIVE LOGITS
     GetType
    0.07
    34
    0.06
    \V
    0.06
    Little
    0.06
     Ext
    0.06
     gender
    0.06
    зация
    0.06
    .sz
    0.06
    Wind
    0.06
     Aw
    0.06
    Activations Density 0.003%

    No Known Activations