© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 92013
    Prev
    Next
    INDEX
    Explanations

    spell

    np_max-act · gemini-2.0-flash

    The neuron fires on fragments of “cauldron” (and related brewing terms) in potion‐making contexts, i.e. it detects mentions of the magic cauldron.

    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
    는지
    -0.07
    빌
    -0.06
     rake
    -0.06
    [M
    -0.06
    liği
    -0.06
     Initially
    -0.06
    ف
    -0.06
    (cid
    -0.06
     surpass
    -0.06
     PPP
    -0.06
    POSITIVE LOGITS
     ¬
    0.07
     rearr
    0.06
     №
    0.06
     Http
    0.06
     succeed
    0.06
    (nx
    0.06
     poslední
    0.06
     lodge
    0.06
     즐
    0.06
     bulunmaktadır
    0.06
    Activations Density 0.011%

    No Known Activations