Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85511
    Prev
    Next
    INDEX
    Explanations

    Electromagnetic/magnetic field treatments

    np_max-act · gemini-2.0-flash

    information related to therapeutic applications and advancements in medical treatments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on the names of specific therapeutic modalities or treatment techniques (e.g. ultrasound, laser therapy, electromagnetic field therapies).

    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
    FIT
    -0.07
    (note
    -0.06
    ote
    -0.06
    .Redirect
    -0.06
    .k
    -0.06
     "/");↵
    -0.06
     点
    -0.06
     Lam
    -0.06
    _dead
    -0.06
    иш
    -0.06
    POSITIVE LOGITS
    /big
    0.07
     возможность
    0.07
     asym
    0.06
     début
    0.06
     uncommon
    0.06
     breached
    0.06
     сбор
    0.06
    Specification
    0.06
     sắc
    0.06
    では
    0.06
    Activations Density 0.033%

    No Known Activations