© 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. 16179
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related references

    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
    ayar
    -0.08
    ÑĢÑĸÑĩ
    -0.07
    ucceed
    -0.07
    "|
    -0.07
    شتر
    -0.07
    ãĥ³ãĥIJ
    -0.07
    аÑĢÑĸв
    -0.07
    claimer
    -0.07
    êu
    -0.06
    amil
    -0.06
    POSITIVE LOGITS
    acon
    0.06
     ActionTypes
    0.06
    ogan
    0.05
     TypeInfo
    0.05
     scar
    0.05
     Khal
    0.05
     clam
    0.05
     Brew
    0.05
    afa
    0.05
     actionTypes
    0.05
    Activations Density 0.068%

    No Known Activations