© 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. 42068
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to performance metrics

    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
    anca
    -0.07
    AXB
    -0.07
    erland
    -0.06
    idian
    -0.06
    aram
    -0.06
    ª½
    -0.06
     pitches
    -0.06
    StateException
    -0.06
    mada
    -0.06
    amber
    -0.06
    POSITIVE LOGITS
     overall
    0.07
    overall
    0.06
     limburg
    0.06
     Overall
    0.06
     Rat
    0.06
    .readValue
    0.06
    enez
    0.06
    /ns
    0.05
    igli
    0.05
     ratios
    0.05
    Activations Density 0.004%

    No Known Activations