© 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. 125910
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate specialization in various fields or 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
    ìĥģìĿĺ
    -0.07
    _DECLARE
    -0.06
    um
    -0.06
    _some
    -0.06
    reserve
    -0.06
    Îļα
    -0.06
    ilet
    -0.06
    á»ķ
    -0.06
    åĮ
    -0.06
    canf
    -0.06
    POSITIVE LOGITS
    827
    0.07
     issues
    0.06
    iere
    0.06
    Latch
    0.06
    -house
    0.06
     providing
    0.06
     custom
    0.06
    ahir
    0.06
    verse
    0.05
     adults
    0.05
    Activations Density 0.007%

    No Known Activations