© 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. 78627
    Prev
    Next
    INDEX
    Explanations

    references to software setup and troubleshooting issues

    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
    instead
    -0.06
    Hope
    -0.06
    lasses
    -0.06
    xls
    -0.06
    Instead
    -0.06
     Hod
    -0.06
     Hope
    -0.06
     Forge
    -0.06
    æŁIJ
    -0.06
     hope
    -0.06
    POSITIVE LOGITS
     correct
    0.09
     correctness
    0.08
    æŃ£ç¡®
    0.07
     correctly
    0.07
    ç¡®
    0.07
     nowhere
    0.07
    _correct
    0.07
     indeed
    0.07
     checked
    0.07
    correct
    0.07
    Activations Density 0.014%

    No Known Activations