© 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. 43417
    Prev
    Next
    INDEX
    Explanations

    distribution

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of pharmacokinetic parameters (like clearance, volume of distribution, half-life, and related numerical values) in the text.

    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
    och
    -0.07
    .asc
    -0.06
    -Length
    -0.06
     Hansen
    -0.06
    chte
    -0.06
     Medical
    -0.06
     lässt
    -0.06
     PhD
    -0.06
     />,↵
    -0.06
     Parkinson
    -0.06
    POSITIVE LOGITS
     공동
    0.06
     gallon
    0.06
    _FM
    0.06
    (vp
    0.06
    후기
    0.06
    009
    0.06
     incentiv
    0.06
    _VC
    0.06
     مخروط
    0.06
     пон
    0.06
    Activations Density 0.005%

    No Known Activations