© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126413
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “sepsis” (i.e. the subword tokens spelling out “se ‑ ps ‑ is”).

    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
     mistr
    -0.07
    řad
    -0.07
     Women
    -0.07
     сообщ
    -0.07
    .onPause
    -0.06
    وفي
    -0.06
    getReference
    -0.06
     Střed
    -0.06
    (clock
    -0.06
    ansk
    -0.06
    POSITIVE LOGITS
     debian
    0.07
     두
    0.07
    ?),
    0.07
     (↵↵
    0.07
     si
    0.06
     공식
    0.06
    zig
    0.06
     celebrity
    0.06
     influ
    0.06
    EDIUM
    0.06
    Activations Density 0.001%

    No Known Activations