© 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. 56008
    Prev
    Next
    INDEX
    Explanations

    ranges and numerical values associated with measurements or statistics

    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
    alley
    -0.07
    ENOMEM
    -0.06
    HITE
    -0.06
     Discipline
    -0.06
    é§IJ
    -0.06
    schemas
    -0.06
    strcasecmp
    -0.06
    alion
    -0.06
    amedi
    -0.06
    (strict
    -0.06
    POSITIVE LOGITS
     range
    0.09
    ptal
    0.08
     ÑĢайоне
    0.07
     tes
    0.06
    range
    0.06
    .Cloud
    0.06
    Banner
    0.06
    aptor
    0.06
    ossier
    0.06
    wner
    0.06
    Activations Density 0.014%

    No Known Activations