© 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. 17-LLAMASCOPE-RES-131K
    11. 57877
    Prev
    Next
    INDEX
    Explanations

    numerical data and citations related to scientific research

    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
    ombat
    -0.07
    iasi
    -0.06
    uel
    -0.06
    ude
    -0.06
    ÏĦιο
    -0.06
    logg
    -0.06
    aska
    -0.06
     unacceptable
    -0.06
    dit
    -0.06
    asio
    -0.06
    POSITIVE LOGITS
    они
    0.07
    रण
    0.06
    æº
    0.06
    .asm
    0.06
     Hind
    0.06
     dar
    0.06
     Polo
    0.06
    unist
    0.06
     Brom
    0.06
    atak
    0.06
    Activations Density 0.026%

    No Known Activations