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. 55154
    Prev
    Next
    INDEX
    Explanations

    etiology, iology

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the root “etiolog-” (as in “etiology,” “etiologic,” 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
     CONVERT
    -0.07
    Coverage
    -0.07
     USS
    -0.06
     příspěv
    -0.06
     benchmark
    -0.06
     passing
    -0.06
     PUSH
    -0.06
    Dice
    -0.06
     orbital
    -0.06
     khắc
    -0.06
    POSITIVE LOGITS
     Elle
    0.07
     lå
    0.07
     factors
    0.07
    xEB
    0.06
     Тем
    0.06
    _IF
    0.06
    batis
    0.06
     Maine
    0.06
    ohl
    0.06
     Leo
    0.06
    Activations Density 0.005%

    No Known Activations