© 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. 129780
    Prev
    Next
    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash

    The neuron fires on the standard Anders‐brief boilerplate describing appointed counsel’s motion to withdraw—i.e. the passages where counsel “has filed a brief” stating the appeal is wholly frivolous.

    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
    [path
    -0.07
    `)↵
    -0.06
    _mux
    -0.06
    _que
    -0.06
    .vel
    -0.06
    атем
    -0.06
    話
    -0.06
    edium
    -0.06
    ENCHMARK
    -0.06
    RESP
    -0.06
    POSITIVE LOGITS
    odní
    0.07
     dotted
    0.07
     française
    0.06
    :[[
    0.06
     Boundary
    0.06
     حوزه
    0.06
     ев
    0.06
    417
    0.06
    inker
    0.06
    .dart
    0.06
    Activations Density 0.002%

    No Known Activations