© 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. 973
    Prev
    Next
    INDEX
    Explanations

    terms associated with files and data management

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

    Grammatical punctuation marks and connecting phrases that join clauses or introduce new information 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
    ael
    -0.07
    onor
    -0.06
     novel
    -0.06
    ae
    -0.06
     Ends
    -0.06
     Novel
    -0.06
    ï
    -0.06
     conspir
    -0.06
     then
    -0.06
     otherwise
    -0.06
    POSITIVE LOGITS
    ECTOR
    0.10
     obvious
    0.08
    either
    0.07
    788
    0.07
    again
    0.07
    okie
    0.07
     either
    0.07
     depending
    0.07
    óż
    0.06
     EITHER
    0.06
    Activations Density 0.024%

    No Known Activations