© 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. 87734
    Prev
    Next
    INDEX
    Explanations

    financial statistics and performance metrics

    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
    umas
    -0.08
    éŁ¿
    -0.07
    inch
    -0.07
    alous
    -0.07
    @brief
    -0.07
     jadx
    -0.06
    iland
    -0.06
     volumes
    -0.06
    erk
    -0.06
    //{{
    -0.06
    POSITIVE LOGITS
     performance
    0.06
     positive
    0.06
    ann
    0.06
     growth
    0.06
     Sheridan
    0.06
     negative
    0.06
    hesion
    0.06
    æĶ¶çĽĬ
    0.06
     Performance
    0.05
     underlying
    0.05
    Activations Density 0.012%

    No Known Activations