© 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. 78036
    Prev
    Next
    INDEX
    Explanations

    references to PDF files and documents

    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
    arde
    -0.07
    oret
    -0.06
    ade
    -0.06
    ful
    -0.06
    rng
    -0.06
    datable
    -0.06
     Engl
    -0.06
    use
    -0.06
    FUL
    -0.06
    otes
    -0.05
    POSITIVE LOGITS
    s
    0.10
    scape
    0.10
    417
    0.09
    Sharper
    0.08
    sand
    0.08
    sak
    0.08
    sam
    0.08
    soc
    0.08
    sWith
    0.07
    Assignable
    0.07
    Activations Density 0.009%

    No Known Activations