© 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. 15-RESID-POST-AA
    11. 9006
    Prev
    Next
    INDEX
    Explanations

    drug use

    np_max-act · gemini-2.0-flash

    mentions of drugs or substance use, especially words about consumption methods and the onset/duration/effects of those substances.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shattered
    -0.08
    (px
    -0.07
     Expansion
    -0.07
     ولي
    -0.07
     radians
    -0.07
    压
    -0.07
    $↵↵
    -0.07
     establishes
    -0.07
    .getSelection
    -0.07
    !↵↵
    -0.06
    POSITIVE LOGITS
    onya
    0.06
     incontri
    0.06
    -machine
    0.06
     CNC
    0.06
     mitigate
    0.06
     mitig
    0.06
     німець
    0.06
     nIndex
    0.06
     prot
    0.06
     clay
    0.06
    Activations Density 0.118%

    No Known Activations