© 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. 77543
    Prev
    Next
    INDEX
    Explanations

    references to historical atrocities and their consequences

    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
     Orta
    -0.08
    Ùħبر
    -0.07
    âĢ«
    -0.07
     minul
    -0.07
     GÃľ
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
     ########################################################################
    -0.07
     Kür
    -0.07
    imd
    -0.07
    onymous
    -0.07
    POSITIVE LOGITS
     estimates
    0.08
     Estimates
    0.07
     between
    0.07
     figure
    0.07
     total
    0.07
     figures
    0.06
     coer
    0.06
     according
    0.06
     "
    0.06
     estimated
    0.06
    Activations Density 0.023%

    No Known Activations