© 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 EvalsExportsinterp-engineNEWAPI 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. 54726
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    baugh
    -0.07
    inus
    -0.07
    ankind
    -0.07
    arrass
    -0.06
    abay
    -0.06
    sko
    -0.06
    unas
    -0.06
    梨
    -0.06
    mando
    -0.06
    334
    -0.06
    POSITIVE LOGITS
    çĢ¬
    0.07
    ance
    0.07
    ker
    0.07
    Ø©
    0.07
    hape
    0.07
    aÄį
    0.06
    ur
    0.06
    th
    0.06
    onga
    0.06
    esson
    0.06
    Activations Density 0.006%

    No Known Activations