© 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. 58721
    Prev
    Next
    INDEX
    Explanations

    numbers and scientific notations or references

    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
    /MPL
    -0.08
    ymes
    -0.08
    ersonic
    -0.07
    .sax
    -0.07
    ccoli
    -0.07
    RuleContext
    -0.07
    ckill
    -0.07
    ãģıãĤĵ
    -0.07
    ĥn
    -0.07
    erdale
    -0.07
    POSITIVE LOGITS
    eff
    0.05
     rein
    0.05
    ec
    0.05
    ahl
    0.05
     Holland
    0.05
     region
    0.05
     sacred
    0.05
    oder
    0.05
    ee
    0.05
    ahr
    0.05
    Activations Density 0.006%

    No Known Activations