© 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
    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. 20739
    Prev
    Next
    INDEX
    Explanations

    medical trials

    np_max-act · gemini-2.0-flash

    clinical trial terminology and results related to the efficacy and safety of medical treatments.

    oai_token-act-pair · gpt-4o-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
     возник
    -0.06
    bearer
    -0.06
    ays
    -0.06
     Clay
    -0.06
    each
    -0.06
     було
    -0.06
     commenter
    -0.06
    NSURL
    -0.06
    between
    -0.06
     Deleted
    -0.06
    POSITIVE LOGITS
     [{'
    0.07
    マ
    0.07
     cant
    0.07
    ROLS
    0.07
    		    		
    0.06
    _INCLUDED
    0.06
    :///
    0.06
    을
    0.06
    rieve
    0.06
    υσ
    0.06
    Activations Density 0.043%

    No Known Activations