© 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. 55414
    Prev
    Next
    INDEX
    Explanations

    rolling, ing

    np_max-act · gemini-2.0-flash

    The neuron fires on terms involved in specifying log‐to‐file or rolling‐file appender configuration (e.g. filenames, “Rolling,” “FileAppender,” etc.).

    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
    symbols
    -0.06
     IsNot
    -0.06
    bij
    -0.06
    γραφ
    -0.06
    _wave
    -0.06
     Flutter
    -0.06
    undry
    -0.06
     GenerationType
    -0.06
     빌
    -0.06
     Baptist
    -0.06
    POSITIVE LOGITS
     모두
    0.07
    ovol
    0.07
     ром
    0.07
    lickr
    0.06
     mitt
    0.06
     사진
    0.06
     Dems
    0.06
    Usu
    0.06
    τια
    0.06
    '";↵
    0.06
    Activations Density 0.005%

    No Known Activations