© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44593
    Prev
    Next
    INDEX
    Explanations

    antagon

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of molecular inhibitors or antagonists in biomedical contexts.

    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
     sieve
    -0.08
     rein
    -0.07
     fleeting
    -0.07
    _YEAR
    -0.07
     collects
    -0.07
     POSS
    -0.07
     LIB
    -0.06
    Lee
    -0.06
     Firebase
    -0.06
     bills
    -0.06
    POSITIVE LOGITS
     antagon
    0.09
    anyl
    0.08
     protagon
    0.08
     antagonist
    0.08
    �
    0.07
    tag
    0.07
    minimum
    0.07
     Como
    0.07
     mM
    0.07
    /tasks
    0.07
    Activations Density 0.004%

    No Known Activations