© 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. 109869
    Prev
    Next
    INDEX
    Explanations

    hinge

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of hinge components or hinge‐related structures (e.g. “hinge,” “hinge assembly,” “hinge mechanism”).

    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
     queer
    -0.06
    Terrain
    -0.06
    [count
    -0.06
     kamp
    -0.06
     actor
    -0.06
    Od
    -0.06
     potom
    -0.06
    /message
    -0.06
    levard
    -0.06
     anál
    -0.06
    POSITIVE LOGITS
     hinge
    0.11
     hinges
    0.09
     glue
    0.07
    verse
    0.07
     folding
    0.07
     hete
    0.07
    inged
    0.07
     champagne
    0.06
    elves
    0.06
    helm
    0.06
    Activations Density 0.001%

    No Known Activations