© 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. 93751
    Prev
    Next
    INDEX
    Explanations

    medical emergencies

    np_max-act · gemini-2.0-flash

    Detects mentions of first-aid and emergency medical assistance or instructions.

    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
    observable
    -0.07
     faint
    -0.07
    .quest
    -0.06
     ministers
    -0.06
    rpm
    -0.06
     pros
    -0.06
    :black
    -0.06
    /gin
    -0.06
    ]interface
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    ancellor
    0.07
     Boolean
    0.07
     gồm
    0.06
     заболевания
    0.06
    oning
    0.06
    ことが
    0.06
     */
↵
↵
    0.06
    .Orientation
    0.06
     migraine
    0.06
    toggleClass
    0.06
    Activations Density 0.023%

    No Known Activations