© 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. 15-LLAMASCOPE-RES-131K
    11. 89288
    Prev
    Next
    INDEX
    Explanations

    key subjects or entities within a narrative context

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

    Noun phrases and pronouns that function as reference expressions, often with definite articles, creating textual cohesion by pointing to entities or concepts established in the discourse.

    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
    indy
    -0.07
    ábado
    -0.07
     Insight
    -0.06
    ugins
    -0.06
    igin
    -0.06
    ahl
    -0.06
    andon
    -0.06
    olest
    -0.06
    ffa
    -0.06
    igli
    -0.06
    POSITIVE LOGITS
    spor
    0.07
    adians
    0.07
     Gould
    0.07
    mi
    0.06
     name
    0.06
     kâ
    0.06
    nam
    0.06
    /xhtml
    0.06
     seldom
    0.06
     maj
    0.06
    Activations Density 0.014%

    No Known Activations