© 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. 11-RESID-POST-AA
    11. 54033
    Prev
    Next
    INDEX
    Explanations

    medical findings

    np_max-act · gemini-2.0-flash

    The neuron detects language reporting patient outcomes or recovery status (e.g. healed, cleared, present) in clinical follow-up studies.

    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
    48
    -0.07
    .cover
    -0.07
    @extends
    -0.07
    GCC
    -0.06
     one
    -0.06
     flexGrow
    -0.06
    398
    -0.06
     between
    -0.06
    LAY
    -0.06
     Oilers
    -0.06
    POSITIVE LOGITS
    зано
    0.07
    ollower
    0.06
     отказ
    0.06
    .Metadata
    0.06
    ันม
    0.06
    DoubleClick
    0.06
     पर
    0.06
    аем
    0.06
     رج
    0.06
     filesystem
    0.06
    Activations Density 0.202%

    No Known Activations