© 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. 127179
    Prev
    Next
    INDEX
    Explanations

    terms related to comments and reviews

    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
    deen
    -0.08
    sst
    -0.07
    sus
    -0.07
    èķ
    -0.06
    SCAN
    -0.06
    udi
    -0.06
    sie
    -0.06
    shr
    -0.06
    afari
    -0.06
    -Ñħ
    -0.06
    POSITIVE LOGITS
    ekil
    0.07
    .fn
    0.07
    eting
    0.06
    ç´¯
    0.06
     evid
    0.06
    onec
    0.06
     Hubb
    0.06
    ettle
    0.06
     Garner
    0.06
    655
    0.06
    Activations Density 0.000%

    No Known Activations