© 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. 76628
    Prev
    Next
    INDEX
    Explanations

    various types of numerical data and document retrieval 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
    forman
    -0.09
    elpers
    -0.08
    elps
    -0.07
    aniu
    -0.07
     gord
    -0.07
    åĥķ
    -0.07
    -inner
    -0.07
    amam
    -0.07
    ruba
    -0.07
    lect
    -0.07
    POSITIVE LOGITS
    ah
    0.07
    de
    0.06
     Economy
    0.06
    459
    0.06
    нок
    0.06
    antine
    0.06
    {{
    0.06
     lit
    0.05
    -p
    0.05
     audio
    0.05
    Activations Density 0.004%

    No Known Activations