© 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. 30532
    Prev
    Next
    INDEX
    Explanations

    xe

    np_max-act · gemini-2.0-flash

    The neuron flags hexadecimal byte‐escape sequences (e.g. “\x80”, “\x9c”, “\xe2”, etc.) embedded in the text.

    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
     tổ
    -0.07
    Odd
    -0.07
    nop
    -0.06
    求
    -0.06
    -Cal
    -0.06
    Mad
    -0.06
    ناء
    -0.06
     BU
    -0.06
    改革
    -0.06
    -क
    -0.06
    POSITIVE LOGITS
    ren
    0.07
     XElement
    0.07
     lay
    0.07
    (el
    0.07
     ー
    0.06
    Annotation
    0.06
    den
    0.06
    .clientHeight
    0.06
     Lever
    0.06
    _CSR
    0.06
    Activations Density 0.001%

    No Known Activations