Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55630
    Prev
    Next
    INDEX
    Explanations

    appeal

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the procedural term “appeal” (and closely related filing or dismissal contexts) in legal documents.

    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
     dul
    -0.07
    Deprecated
    -0.07
    лиш
    -0.06
    ิมพ
    -0.06
    Validate
    -0.06
     labels
    -0.06
     Responsible
    -0.06
     toys
    -0.06
     officer
    -0.06
     ink
    -0.06
    POSITIVE LOGITS
     ngữ
    0.08
    toDouble
    0.07
    Continue
    0.07
    .addField
    0.07
    emplates
    0.07
     العربية
    0.07
    (火
    0.07
     Gä
    0.06
    )、
    0.06
     ')';↵
    0.06
    Activations Density 0.004%

    No Known Activations