© 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. 27281
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical discussions and conditions in proofs

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

    LaTeX counter values for remarks in academic documents, or grammatical connecting elements (conjunctions, prepositions, punctuation) that join clauses in sentences.

    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
    allis
    -0.09
    olla
    -0.08
     defaultMessage
    -0.08
    senal
    -0.08
    ipment
    -0.08
    еÑĤÑĮÑģÑı
    -0.08
    .scalablytyped
    -0.08
    uja
    -0.08
    .openConnection
    -0.08
     knull
    -0.08
    POSITIVE LOGITS
     non
    0.07
    <![
    0.06
    ïĢ
    0.06
     "
    0.06
     separately
    0.06
     _{}
    0.06
     independently
    0.05
     vice
    0.05
     sup
    0.05
    :↵
    0.05
    Activations Density 0.024%

    No Known Activations