© 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. 128867
    Prev
    Next
    INDEX
    Explanations

    recovery

    np_max-act · gemini-2.0-flash

    This neuron detects comparative outcome terms in clinical trial summaries—words that quantify improvements (e.g. “shorter,” “faster,” “less,” “recovery,” etc.).

    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
    _HEX
    -0.07
    .storage
    -0.07
     entfer
    -0.06
     chaud
    -0.06
    _comments
    -0.06
    _ack
    -0.06
     thận
    -0.06
     vascular
    -0.06
     DG
    -0.05
     Karen
    -0.05
    POSITIVE LOGITS
    ніч
    0.07
     Cristina
    0.06
    ltr
    0.06
     fatalError
    0.06
    .bit
    0.06
     Panama
    0.06
     logically
    0.06
     FIFA
    0.06
     SOCIAL
    0.06
    Apparently
    0.06
    Activations Density 0.015%

    No Known Activations