© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110081
    Prev
    Next
    INDEX
    Explanations

    inside information

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on the word “inside” (and by extension “insider”/“inside information”), marking references to secret or internal knowledge.

    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
     fq
    -0.07
     remembered
    -0.07
     remembers
    -0.07
     MAK
    -0.06
     complement
    -0.06
     arriving
    -0.06
    ца
    -0.06
    _abort
    -0.06
     dwarf
    -0.06
    ลงท
    -0.06
    POSITIVE LOGITS
     ตอน
    0.07
     muse
    0.06
    (directory
    0.06
    _optional
    0.06
    таки
    0.06
     Millionen
    0.06
    гар
    0.06
     نظامی
    0.06
    _RESULT
    0.06
     healthcare
    0.06
    Activations Density 0.098%

    No Known Activations