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. 85528
    Prev
    Next
    INDEX
    Explanations

    com

    np_max-act · gemini-2.0-flash

    The neuron detects orthographic fragments of fungal taxonomic terms (e.g. parts of “Ascomycota,” “ascomycete,” “ascospore,” etc.).

    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
    .Drawing
    -0.07
    666
    -0.07
     BrowserModule
    -0.07
     Infinite
    -0.06
     铁
    -0.06
     Reyn
    -0.06
     Zero
    -0.06
     ALL
    -0.06
     exclusion
    -0.06
     Desmond
    -0.06
    POSITIVE LOGITS
    -paying
    0.06
    ennie
    0.06
    .pat
    0.06
     kuchy
    0.06
    рип
    0.06
    iger
    0.06
    (email
    0.06
     believer
    0.06
     acted
    0.06
     dom
    0.06
    Activations Density 0.002%

    No Known Activations