© 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. 69204
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to geometric and mathematical spaces

    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
    á»ijt
    -0.07
    artner
    -0.07
    åľ¨åľ°
    -0.06
     Swinger
    -0.06
    fully
    -0.06
     äºİ
    -0.06
    ť
    -0.06
     çľ
    -0.06
    inha
    -0.06
    venes
    -0.06
    POSITIVE LOGITS
    -wide
    0.08
    thinkable
    0.07
    -based
    0.07
    /world
    0.06
    LOTS
    0.06
    SizeMode
    0.06
     forState
    0.06
     nutshell
    0.06
    based
    0.06
    ÛĮدا
    0.06
    Activations Density 0.067%

    No Known Activations