© 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. 15-LLAMASCOPE-RES-131K
    11. 90208
    Prev
    Next
    INDEX
    Explanations

    mentions of documents and their revisions or related scholarly references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical terms that signal the type, scope, or nature of a document, often appearing in context that refers to the document itself or establishes limitations of the content being discussed.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ạnh
    -0.07
    iez
    -0.07
    boru
    -0.07
    bor
    -0.06
    ilot
    -0.06
    antu
    -0.06
    emin
    -0.06
    dish
    -0.06
    ult
    -0.06
    _each
    -0.06
    POSITIVE LOGITS
     nor
    0.18
     anymore
    0.18
     Nor
    0.12
     neither
    0.11
     unless
    0.11
    Nor
    0.11
    nor
    0.10
    unless
    0.10
    à¹ĥà¸Ķ
    0.09
     either
    0.09
    Activations Density 0.058%

    No Known Activations