© 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. 57371
    Prev
    Next
    INDEX
    Explanations

    terms related to performance metrics and outcomes

    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
    elin
    -0.08
    itech
    -0.08
    .scalablytyped
    -0.08
    /XMLSchema
    -0.07
    _REUSE
    -0.07
    uegos
    -0.07
    orthy
    -0.07
    ymax
    -0.07
    ynet
    -0.07
    >"+↵
    -0.07
    POSITIVE LOGITS
     Norris
    0.07
    sen
    0.07
    tem
    0.06
     Corey
    0.06
     Sen
    0.06
    çe
    0.06
    altar
    0.06
     bam
    0.06
     Ok
    0.06
     simul
    0.06
    Activations Density 0.003%

    No Known Activations