© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16808
    Prev
    Next
    INDEX
    Explanations

    descriptions of serene and tranquil environments

    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
     turno
    -0.07
    Äij
    -0.06
    esty
    -0.06
    hurst
    -0.06
    itti
    -0.06
    errick
    -0.06
     ung
    -0.06
    uç
    -0.06
    EI
    -0.06
    моÑĢ
    -0.06
    POSITIVE LOGITS
     quiet
    0.11
     peace
    0.10
     Quiet
    0.09
    quiet
    0.09
     quietly
    0.09
     calm
    0.08
    Quiet
    0.08
    ude
    0.08
     calming
    0.08
     Peace
    0.07
    Activations Density 0.037%

    No Known Activations