© 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. 124799
    Prev
    Next
    INDEX
    Explanations

    Something

    np_max-act · gemini-2.0-flash

    This neuron detects uses of the word “something.”

    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
     raid
    -0.07
    _KeyPress
    -0.07
     ids
    -0.07
    _ans
    -0.07
    _ids
    -0.07
     all
    -0.07
    Free
    -0.07
     bic
    -0.07
     RS
    -0.07
     Corps
    -0.07
    POSITIVE LOGITS
     something
    0.18
     Something
    0.14
    something
    0.14
    Something
    0.13
     someone
    0.10
    nothing
    0.10
    omething
    0.09
     somewhere
    0.09
    someone
    0.09
     Someone
    0.09
    Activations Density 0.053%

    No Known Activations