© 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. 57622
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uniqueness or exceptional characteristics

    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
     bat
    -0.07
     Uns
    -0.06
     uns
    -0.06
     Batt
    -0.06
    èIJ½ãģ¡
    -0.06
     ste
    -0.06
    onse
    -0.06
    onet
    -0.06
    Normal
    -0.06
    onest
    -0.06
    POSITIVE LOGITS
     nowhere
    0.14
     nobody
    0.14
     few
    0.11
     Nobody
    0.10
     никÑĤо
    0.10
    few
    0.10
     ONLY
    0.10
     only
    0.10
    only
    0.10
    Nobody
    0.09
    Activations Density 0.027%

    No Known Activations