© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 124991
    Prev
    Next
    INDEX
    Explanations

    code or file paths

    np_max-act · gemini-2.0-flash

    This neuron remains inactive and does not reliably detect or respond to any token patterns.

    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
     speculated
    -0.07
     takeaway
    -0.07
    дан
    -0.06
     Ко
    -0.06
     Gotham
    -0.06
    乾
    -0.06
    ultiple
    -0.06
    乱
    -0.06
    پر
    -0.06
    فران
    -0.06
    POSITIVE LOGITS
     Curso
    0.08
     lt
    0.07
     Scope
    0.07
    .addAttribute
    0.07
    /std
    0.07
    ічний
    0.07
     пра
    0.06
    ประเทศ
    0.06
    wolf
    0.06
    bsub
    0.06
    Activations Density 0.020%

    No Known Activations