© 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. 49548
    Prev
    Next
    INDEX
    Explanations

    male/female

    np_max-act · gemini-2.0-flash

    words related to insects and their ecological characteristics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on references to an animal’s biological sex or sexual dimorphism (e.g. distinctions between male vs. female).

    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
     Durant
    -0.07
    劃
    -0.06
    ुरस
    -0.06
    ifestyles
    -0.06
    ementia
    -0.06
    _gift
    -0.06
     Th
    -0.06
    透
    -0.06
     myth
    -0.06
    .Xna
    -0.06
    POSITIVE LOGITS
    精
    0.07
     except
    0.07
     оформ
    0.07
     ´
    0.07
     TObject
    0.07
     začí
    0.07
     sacked
    0.06
    Proof
    0.06
    _commit
    0.06
    _nn
    0.06
    Activations Density 0.007%

    No Known Activations