© 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. 40308
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistical data

    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
    åį
    -0.06
     ch
    -0.06
     cr
    -0.06
     parallel
    -0.06
    бо
    -0.06
    ursal
    -0.06
     big
    -0.05
     internal
    -0.05
    ↵
    -0.05
     Jasper
    -0.05
    POSITIVE LOGITS
     âĵĺ
    0.09
    inyin
    0.08
    Ðİ
    0.08
    tam
    0.07
    otionEvent
    0.07
    ãĥ«ãĥī
    0.07
    ulu
    0.07
    ó
    0.07
     ë¹Ľ
    0.07
    ãĤ¦ãĤ¹
    0.07
    Activations Density 0.000%

    No Known Activations