Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77291
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and encouragement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argent
    -0.08
    ObjectContext
    -0.08
    Ctx
    -0.07
    odore
    -0.07
    uae
    -0.06
    alse
    -0.06
    emade
    -0.06
    ock
    -0.06
    ông
    -0.06
    ew
    -0.06
    POSITIVE LOGITS
     Stout
    0.06
     recipro
    0.06
     prio
    0.06
    irut
    0.06
     Dud
    0.06
    /on
    0.06
     Bilg
    0.06
    eyin
    0.06
    667
    0.06
    ossal
    0.06
    Activations Density 0.009%

    No Known Activations