© 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. 126345
    Prev
    Next
    INDEX
    Explanations

    Missing environment variables/files

    np_max-act · gemini-2.0-flash

    bash scripting commands and related variables for setting up environments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on human‐readable status, usage, and error message words (the labels inside echo/print statements).

    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
     Gina
    -0.06
     vendors
    -0.06
     videos
    -0.06
     problémy
    -0.06
    국의
    -0.06
    它
    -0.06
     안전
    -0.06
     Survival
    -0.05
     Related
    -0.05
     pracov
    -0.05
    POSITIVE LOGITS
     kuş
    0.08
     [@
    0.07
     azimuth
    0.07
     Structures
    0.07
    /loose
    0.06
    adesh
    0.06
    основ
    0.06
    -array
    0.06
     ninety
    0.06
    apore
    0.06
    Activations Density 0.012%

    No Known Activations