© 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. 30662
    Prev
    Next
    INDEX
    Explanations

    improvement

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of clinical improvement or positive treatment response (e.g. “improved,” “resolved,” “treated,” “dramatic improvement”).

    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
    ція
    -0.07
     blind
    -0.07
     sealing
    -0.06
     tote
    -0.06
    би
    -0.06
     Dashboard
    -0.06
     FLT
    -0.06
    ,'%
    -0.06
    EPROM
    -0.06
     mnoha
    -0.06
    POSITIVE LOGITS
    eq
    0.06
    _segments
    0.06
    َى
    0.06
    _picture
    0.06
     Showcase
    0.06
     gamm
    0.06
     bah
    0.06
    eden
    0.06
    remote
    0.06
     Wins
    0.06
    Activations Density 0.025%

    No Known Activations