© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91276
    Prev
    Next
    INDEX
    Explanations

    sheep

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “sheep” (including its “ep” subtoken), i.e. it detects mentions of the animal sheep.

    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
    ิทย
    -0.07
    廠
    -0.07
     dáng
    -0.07
     písem
    -0.07
     Roland
    -0.06
    วร
    -0.06
     X
    -0.06
     filmpjes
    -0.06
     ['.
    -0.06
     siêu
    -0.06
    POSITIVE LOGITS
     sheep
    0.15
     Sheep
    0.12
     Shepherd
    0.10
     lamb
    0.09
     goat
    0.09
     flock
    0.09
     shepherd
    0.08
     Lamb
    0.08
    091
    0.08
     Goat
    0.07
    Activations Density 0.006%

    No Known Activations