© 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. 12774
    Prev
    Next
    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that contain an underscore (e.g., parts of variable or filename identifiers with “_”).

    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
    说
    -0.08
    dbuf
    -0.06
    ève
    -0.06
     threat
    -0.06
    ]'↵
    -0.06
    .d
    -0.06
     PX
    -0.06
    .MouseEvent
    -0.06
    -not
    -0.06
    .play
    -0.06
    POSITIVE LOGITS
     Grip
    0.06
    %M
    0.06
    hardt
    0.06
    خاص
    0.06
     stri
    0.06
     avez
    0.06
    esian
    0.06
    _jwt
    0.06
     یوتی
    0.06
    ulate
    0.06
    Activations Density 0.006%

    No Known Activations