© 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. 55407
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    text related to software licenses and copyright notices.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on C/C++ include directives (i.e. header‐file import lines).

    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
     zda
    -0.06
     unidad
    -0.06
    _sb
    -0.06
     nelze
    -0.06
     �
    -0.06
     recorded
    -0.06
    .EventSystems
    -0.06
    ◆
    -0.06
    组
    -0.06
    	tc
    -0.06
    POSITIVE LOGITS
    _camera
    0.07
     offences
    0.07
    пон
    0.07
     flashlight
    0.06
    datetime
    0.06
    (${
    0.06
    Connor
    0.06
    don
    0.06
     logout
    0.06
    _mot
    0.06
    Activations Density 0.014%

    No Known Activations