© 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. 84370
    Prev
    Next
    INDEX
    Explanations

    character sequences and numerical data typically found in citations 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
    -origin
    -0.07
     Krish
    -0.07
    akest
    -0.07
    atted
    -0.06
    oph
    -0.06
    kara
    -0.06
    urn
    -0.06
     gep
    -0.06
    imals
    -0.06
     diff
    -0.06
    POSITIVE LOGITS
    .UseVisualStyleBackColor
    0.08
    -pills
    0.07
    ott
    0.06
    ossa
    0.06
    duk
    0.06
    âķĹ
    0.06
    زاÙħ
    0.06
    /uploads
    0.06
     MB
    0.06
     Dover
    0.06
    Activations Density 0.031%

    No Known Activations