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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 81352
    Prev
    Next
    INDEX
    Explanations

    player health status

    np_max-act · gemini-2.0-flash

    The neuron flags terms indicating player injury or fitness status (e.g. questionable, injured, fit, ankle).

    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
     Namen
    -0.07
    ंय
    -0.07
    Ctx
    -0.07
     kì
    -0.06
    _TypeInfo
    -0.06
    .savefig
    -0.06
    Appearance
    -0.06
     Mitarbeiter
    -0.06
    ोजन
    -0.06
     WideString
    -0.06
    POSITIVE LOGITS
     scientifically
    0.08
     influences
    0.07
     gallon
    0.07
    Phill
    0.06
     slowed
    0.06
     reports
    0.06
    problems
    0.06
     bypass
    0.06
     include
    0.06
    matches
    0.06
    Activations Density 0.006%

    No Known Activations