© 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. 110805
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash

    The neuron detects model numbers or version designators (often numbers or number‐slash combinations) that identify particular product variants.

    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
     wizards
    -0.07
    ま
    -0.06
     Wells
    -0.06
    egative
    -0.06
    ,key
    -0.06
     seasoning
    -0.06
     Odin
    -0.06
     wont
    -0.06
    oined
    -0.06
    odable
    -0.06
    POSITIVE LOGITS
    .PUT
    0.07
    ago
    0.06
     Yankees
    0.06
     Contact
    0.06
    AGO
    0.06
    <Self
    0.06
    ren
    0.06
    ivement
    0.06
    .DE
    0.06
     ngOnDestroy
    0.06
    Activations Density 0.031%

    No Known Activations