© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126744
    Prev
    Next
    INDEX
    Explanations

    Java or Android version specifications and 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
    bote
    -0.08
    pline
    -0.08
    mav
    -0.08
     tô
    -0.07
     Huffman
    -0.07
    ÙħÙĤ
    -0.07
    @student
    -0.07
    stav
    -0.07
    ether
    -0.07
    Å¡ky
    -0.07
    POSITIVE LOGITS
    oux
    0.07
    ah
    0.06
    оÑģк
    0.06
     Jak
    0.05
    ;amp
    0.05
    anim
    0.05
    uch
    0.05
     Pra
    0.05
    endale
    0.05
    t
    0.05
    Activations Density 0.001%

    No Known Activations