© 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. 15-LLAMASCOPE-RES-131K
    11. 103611
    Prev
    Next
    INDEX
    Explanations

    references to emerging markets or trends in various industries

    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
    esel
    -0.09
    gie
    -0.08
    igham
    -0.07
    amac
    -0.06
    zion
    -0.06
     Bund
    -0.06
    asin
    -0.06
    ernote
    -0.06
     sheet
    -0.06
    ISTRIBUT
    -0.06
    POSITIVE LOGITS
     competing
    0.08
     new
    0.07
    oks
    0.07
     dime
    0.07
    multip
    0.07
    á»ĵi
    0.07
    =~
    0.07
    Ð¡Ðł
    0.06
    031
    0.06
    zens
    0.06
    Activations Density 0.040%

    No Known Activations