© 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. 118857
    Prev
    Next
    INDEX
    Explanations

    phrases related to efficiency and progress in resolving 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
    ouch
    -0.07
    ovich
    -0.07
    -rating
    -0.06
    177
    -0.06
    ãĥ³ãĥĶ
    -0.06
    filt
    -0.06
    HTTPRequest
    -0.06
     upt
    -0.06
     beaut
    -0.06
    ERN
    -0.06
    POSITIVE LOGITS
    ç»ĵæĿŁ
    0.07
    serter
    0.07
     finish
    0.07
     sooner
    0.06
     finished
    0.06
     dosp
    0.06
    areth
    0.06
     Finished
    0.06
    PEnd
    0.06
    ilogue
    0.06
    Activations Density 0.038%

    No Known Activations