© 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. 26548
    Prev
    Next
    INDEX
    Explanations

    major themes and significant terminology related to conferences and academic research

    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
    mant
    -0.07
    .avi
    -0.07
    izzle
    -0.07
    éné
    -0.07
    agua
    -0.06
    armor
    -0.06
    avis
    -0.06
    awe
    -0.06
    rede
    -0.06
    istor
    -0.06
    POSITIVE LOGITS
     Nordic
    0.07
    omics
    0.07
    utos
    0.06
    edited
    0.06
     Glob
    0.06
    788
    0.06
     Asia
    0.06
    inned
    0.06
    tober
    0.06
     conference
    0.05
    Activations Density 0.037%

    No Known Activations