© 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 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. 93779
    Prev
    Next
    INDEX
    Explanations

    statements introducing specific observations or scenarios

    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
     Colony
    -0.06
    él
    -0.06
     Halk
    -0.06
     derivation
    -0.06
    iy
    -0.06
    yo
    -0.06
    .dtype
    -0.06
    ï
    -0.06
    VP
    -0.05
    IL
    -0.05
    POSITIVE LOGITS
     paper
    0.09
    umo
    0.07
    redentials
    0.07
    rowsable
    0.07
    wyn
    0.07
     naturally
    0.07
    HCI
    0.07
    udden
    0.06
    .scalablytyped
    0.06
    esktop
    0.06
    Activations Density 0.033%

    No Known Activations