© 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. 128552
    Prev
    Next
    INDEX
    Explanations

    Game

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming or describing game genres and related descriptors (e.g. “adventure,” “horror,” “mystery,” “puzzle,” “story-driven,” 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
     bidder
    -0.06
    ولد
    -0.06
    �
    -0.06
     fracture
    -0.06
    Fac
    -0.06
     Polo
    -0.06
    Rp
    -0.06
     Ferm
    -0.06
    PointSize
    -0.06
    ovable
    -0.06
    POSITIVE LOGITS
    ikan
    0.07
    ubits
    0.07
     redirection
    0.07
    .Nodes
    0.07
    (metrics
    0.06
    ΑΓ
    0.06
    .SingleOrDefault
    0.06
     дити
    0.06
     hikes
    0.06
     çevre
    0.06
    Activations Density 0.028%

    No Known Activations