© 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. 106
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, conditions, or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    codegen
    -0.07
    ONGL
    -0.07
    .GetLength
    -0.07
    dech
    -0.06
    auen
    -0.06
    imir
    -0.06
    &W
    -0.06
    کتر
    -0.06
    .jobs
    -0.06
     گر
    -0.06
    POSITIVE LOGITS
     or
    0.16
     или
    0.12
     либо
    0.11
     oder
    0.11
    æĪĸèĢħ
    0.11
     hoặc
    0.11
    ê±°ëĤĺ
    0.11
     atau
    0.11
     æĪĸ
    0.11
    æĪĸ
    0.10
    Activations Density 0.040%

    No Known Activations