© 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. 70924
    Prev
    Next
    INDEX
    Explanations

    mentions of volcanic activity and geological processes

    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
    ushima
    -0.06
    latlong
    -0.06
     NotSupportedException
    -0.06
     okul
    -0.06
     vů
    -0.06
    ç¤
    -0.06
    ecko
    -0.06
    pliant
    -0.06
    AYOUT
    -0.06
    AxisSize
    -0.06
    POSITIVE LOGITS
     smoothing
    0.07
     appear
    0.07
     appears
    0.06
    ãĥĥãĥģ
    0.06
    æ¾
    0.06
    Appear
    0.06
    isay
    0.06
     Interrupt
    0.06
     appearances
    0.06
    Enlarge
    0.06
    Activations Density 0.002%

    No Known Activations