© 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. 87597
    Prev
    Next
    INDEX
    Explanations

    statements that imply effects or consequences of an action

    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
    anda
    -0.07
    ساÙĨÛĮ
    -0.07
    ington
    -0.07
    ois
    -0.06
     sucker
    -0.06
     βα
    -0.06
     Sesso
    -0.06
    rious
    -0.06
    ÙĩداÙģ
    -0.06
    andan
    -0.06
    POSITIVE LOGITS
     also
    0.12
    also
    0.10
     Also
    0.10
    Also
    0.09
    ä¹Ł
    0.09
     também
    0.09
     también
    0.08
     cũng
    0.08
     ALSO
    0.08
     aussi
    0.08
    Activations Density 0.038%

    No Known Activations