© 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. 28235
    Prev
    Next
    INDEX
    Explanations

    discrepancies in pricing or financial evaluations

    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
     Lun
    -0.06
    yth
    -0.06
    sti
    -0.06
    elas
    -0.06
     VIN
    -0.05
    yro
    -0.05
    VIN
    -0.05
     sequel
    -0.05
    azi
    -0.05
    sted
    -0.05
    POSITIVE LOGITS
     regional
    0.08
    çĮĽ
    0.07
    etermined
    0.07
    fault
    0.07
    ideon
    0.07
    igne
    0.07
     yerel
    0.07
    onor
    0.07
    orum
    0.07
    ivant
    0.07
    Activations Density 0.019%

    No Known Activations