Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43733
    Prev
    Next
    INDEX
    Explanations

    ot

    np_max-act · gemini-2.0-flash

    The neuron is keyed to the substring “soot,” i.e. it fires on occurrences of the Soot framework’s name in package/import identifiers.

    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
    .Build
    -0.07
     Lenovo
    -0.06
     Hedge
    -0.06
    .NotNull
    -0.06
    .ident
    -0.06
     Tumblr
    -0.06
    irling
    -0.06
    doc
    -0.06
    .Statement
    -0.06
     تبلی
    -0.06
    POSITIVE LOGITS
     wealthiest
    0.07
     وع
    0.07
    447
    0.07
    _ori
    0.07
    -directed
    0.07
    Police
    0.06
    _cou
    0.06
     prowess
    0.06
    	LL
    0.06
     blew
    0.06
    Activations Density 0.000%

    No Known Activations