© 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. 77750
    Prev
    Next
    INDEX
    Explanations

    toxicity and poisoning

    np_max-act · gemini-2.0-flash

    mentions of ingesting potentially harmful substances—poisoning/overdose contexts and related toxicology/emergency guidance

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     دادن
    -0.06
    比較
    -0.06
    _fsm
    -0.06
     كر
    -0.06
     OBS
    -0.06
     footnote
    -0.06
    alm
    -0.06
    ufs
    -0.06
    ddb
    -0.06
    udit
    -0.06
    POSITIVE LOGITS
     progressive
    0.07
     διά
    0.06
    нед
    0.06
    -help
    0.06
    ्षक
    0.06
     Cement
    0.06
     Happ
    0.06
     inevitable
    0.06
    ∏
    0.06
    check
    0.06
    Activations Density 0.017%

    No Known Activations