© 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. 60706
    Prev
    Next
    INDEX
    Explanations

    mentions of hotels and travel arrangements

    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
    _BB
    -0.07
    dum
    -0.07
    hev
    -0.07
    hec
    -0.06
    hee
    -0.06
    ulong
    -0.06
    ÑĤал
    -0.06
    afil
    -0.06
    اÙħÛĮ
    -0.06
    essages
    -0.06
    POSITIVE LOGITS
     return
    0.10
    return
    0.09
    -return
    0.08
     END
    0.08
     end
    0.08
    åĽŀåĪ°
    0.08
    è¿ĶåĽŀ
    0.08
     finish
    0.07
     ends
    0.07
     back
    0.07
    Activations Density 0.009%

    No Known Activations