© 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. 88913
    Prev
    Next
    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the Python “pass” statement (including its appearances in code and discussion).

    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
    ])↵
    -0.06
    Sign
    -0.06
    _SCHED
    -0.06
    .constructor
    -0.06
    >)↵
    -0.06
    )});↵
    -0.06
    NibName
    -0.06
    ))↵
    -0.06
    itmap
    -0.06
     balanced
    -0.06
    POSITIVE LOGITS
    [$_
    0.07
     enforcing
    0.07
    .ok
    0.07
     locating
    0.07
     angered
    0.07
     destek
    0.06
    iydi
    0.06
     commenc
    0.06
     rés
    0.06
     hurdle
    0.06
    Activations Density 0.141%

    No Known Activations