© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30017
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on hyphens and the segments immediately following hyphens in code tokens (e.g. CMake flags, file names, or identifiers that use “-” separators).

    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
     đoán
    -0.07
     Soviets
    -0.06
    Envelope
    -0.06
    venient
    -0.06
    eriod
    -0.06
    (doc
    -0.06
     Prefix
    -0.06
     Kohana
    -0.06
    .utcnow
    -0.06
     cyc
    -0.06
    POSITIVE LOGITS
    *u
    0.08
    _Panel
    0.07
    .*
    0.07
    :"+
    0.07
     Düz
    0.07
     succesfully
    0.06
    왕
    0.06
    +r
    0.06
    +p
    0.06
     Kurdish
    0.06
    Activations Density 0.019%

    No Known Activations