© 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. 71132
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and configuration settings

    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
    UA
    -0.07
    ua
    -0.07
    vek
    -0.06
    stal
    -0.06
    phant
    -0.06
    aver
    -0.06
     whole
    -0.06
    odon
    -0.06
     pur
    -0.06
    adier
    -0.05
    POSITIVE LOGITS
    /default
    0.15
     default
    0.12
     getDefault
    0.11
     Default
    0.11
    default
    0.11
    .DEFAULT
    0.11
    =default
    0.11
    efault
    0.10
    .default
    0.10
    _default
    0.10
    Activations Density 0.029%

    No Known Activations