© 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. 89700
    Prev
    Next
    INDEX
    Explanations

    references to computational processes or algorithms involved in problem-solving

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

    Grammatical function words and technical terms that create relationships between elements in text, often appearing at critical junctures in sentences where they connect ideas or establish context.

    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
    ijkstra
    -0.07
    veau
    -0.07
    èŃ
    -0.07
    ãĤĩãģĨ
    -0.07
    .builders
    -0.06
    è¼
    -0.06
    rrha
    -0.06
    erge
    -0.06
    649
    -0.06
     ÑĢай
    -0.06
    POSITIVE LOGITS
    TestData
    0.06
     rigged
    0.06
     permanently
    0.06
    atoria
    0.06
    _bulk
    0.06
     Abel
    0.06
     trainer
    0.06
     batches
    0.06
     Establish
    0.05
     storage
    0.05
    Activations Density 0.092%

    No Known Activations