© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7883
    Prev
    Next
    INDEX
    Explanations

    Physical activity and injuries

    np_max-act · gemini-2.0-flash

    This neuron detects words that denote contributing risk factors or causes (e.g. repetitive stress, poor mechanics, overweight) for a medical condition.

    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
     Associ
    -0.07
     athlete
    -0.07
     Coff
    -0.06
     wireless
    -0.06
    journal
    -0.06
     ===>
    -0.06
    есс
    -0.06
    记
    -0.06
     fec
    -0.06
    _MP
    -0.06
    POSITIVE LOGITS
    βε
    0.06
    Create
    0.06
    _IMAGE
    0.06
    bind
    0.06
    Ber
    0.06
     ssl
    0.06
     regarded
    0.06
     mutlaka
    0.06
    ισμός
    0.06
    #c
    0.06
    Activations Density 0.043%

    No Known Activations