© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119906
    Prev
    Next
    INDEX
    Explanations

    sentences that explain the purpose of a document

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

    Explanatory or instructional text that introduces, explains, or guides readers through information, often appearing before educational content or as transitions between sections in technical documents, tutorials, or informational resources.

    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
    еÑĢÑĪ
    -0.07
    vé
    -0.06
     mise
    -0.06
    ój
    -0.06
     trial
    -0.06
     Xt
    -0.06
    Codes
    -0.06
    ãĤ¤ãĤ¯
    -0.06
    enk
    -0.06
     codes
    -0.06
    POSITIVE LOGITS
     explanation
    0.12
     explanations
    0.12
     explaining
    0.12
     basic
    0.12
     understanding
    0.11
     explains
    0.11
    basic
    0.11
     Explanation
    0.10
     Understanding
    0.10
    -basic
    0.10
    Activations Density 0.046%

    No Known Activations