© 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. 81404
    Prev
    Next
    INDEX
    Explanations

    key terms associated with rarity and authenticity in collectibles

    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
    ãĤīãģĽ
    -0.06
     Alley
    -0.06
    ByUrl
    -0.06
    amber
    -0.05
    ovna
    -0.05
    ülü
    -0.05
    selector
    -0.05
    stat
    -0.05
     Rack
    -0.05
     deadliest
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
    985
    0.07
    atak
    0.07
    æ´¥
    0.07
    ecz
    0.07
    erville
    0.07
     polishing
    0.06
    kv
    0.06
    ipo
    0.06
     junk
    0.06
    Activations Density 0.005%

    No Known Activations