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. 125789
    Prev
    Next
    INDEX
    Explanations

    Medical research acronyms

    np_max-act · gemini-2.0-flash

    The neuron detects parenthesized uppercase abbreviations (acronyms or initialisms).

    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
    Ctr
    -0.06
    _Up
    -0.06
    ساب
    -0.06
     Пол
    -0.06
    Expr
    -0.06
    enarios
    -0.06
    kup
    -0.06
    (article
    -0.06
     Available
    -0.06
     Loc
    -0.06
    POSITIVE LOGITS
    mazon
    0.07
    works
    0.07
    -quality
    0.06
    _ROLE
    0.06
    ى
    0.06
    rací
    0.06
     честь
    0.06
     sterling
    0.06
     القرن
    0.06
    ُو
    0.06
    Activations Density 0.052%

    No Known Activations