© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14101
    Prev
    Next
    INDEX
    Explanations

    concepts related to hunting and pastoral lifestyles

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãĥĨãĥ«
    -0.08
    輪
    -0.07
     Alo
    -0.07
     Canter
    -0.07
     Demp
    -0.07
    меÑĢик
    -0.07
     Ùħرک
    -0.07
    _charset
    -0.06
    emon
    -0.06
    afür
    -0.06
    POSITIVE LOGITS
     Paleo
    0.10
     Pale
    0.09
     hunter
    0.09
     evolutionary
    0.09
     human
    0.08
     Evolution
    0.08
     Evo
    0.08
     cave
    0.08
     sapi
    0.08
     evolution
    0.07
    Activations Density 0.046%

    No Known Activations