© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 42009
    Prev
    Next
    INDEX
    Explanations

    references to product availability and assistance

    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
     afterwards
    -0.08
    ersist
    -0.08
    filtro
    -0.08
    RITE
    -0.07
    roti
    -0.07
    anship
    -0.07
     afterward
    -0.07
    chwitz
    -0.07
    CISION
    -0.07
    erner
    -0.07
    POSITIVE LOGITS
     already
    0.21
     Already
    0.20
    already
    0.19
    Already
    0.19
     early
    0.17
    early
    0.16
    æĹ©
    0.15
     Early
    0.15
    Early
    0.15
    _already
    0.14
    Activations Density 0.122%

    No Known Activations