© 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. 30475
    Prev
    Next
    INDEX
    Explanations

    line endings and separators

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens referring to line-ending formats (e.g. “CRLF,” “line-ending(s),” “DOS,” “Windows-style”) indicating it’s looking for mentions of newline or carriage-return/line-feed conventions.

    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
    เศรษฐ
    -0.07
    rof
    -0.07
    .Record
    -0.06
    .:.:.
    -0.06
    ADED
    -0.06
    盟
    -0.06
     CONTEXT
    -0.06
    別
    -0.06
    เท
    -0.06
     Baron
    -0.06
    POSITIVE LOGITS
     OSS
    0.08
    (socket
    0.07
     Зем
    0.06
     Cot
    0.06
    variable
    0.06
    (v
    0.06
    -volume
    0.06
     udp
    0.06
     specifier
    0.06
    .channels
    0.06
    Activations Density 0.023%

    No Known Activations