© 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. 15-LLAMASCOPE-RES-131K
    11. 88763
    Prev
    Next
    INDEX
    Explanations

    statistical measures related to confidence intervals and significance testing

    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
    303
    -0.07
     ratios
    -0.06
    agle
    -0.06
    319
    -0.06
    inston
    -0.06
     Ratio
    -0.06
    avers
    -0.06
     ratio
    -0.06
    conds
    -0.06
    éĽ²
    -0.06
    POSITIVE LOGITS
    ModelProperty
    0.07
     tails
    0.07
    ัà¸Ī
    0.06
     distribution
    0.06
    Ace
    0.06
    ROTO
    0.06
    ä¸ĸç´Ģ
    0.06
     BELOW
    0.06
    .Middle
    0.06
     Rounded
    0.06
    Activations Density 0.003%

    No Known Activations