© 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. 62968
    Prev
    Next
    INDEX
    Explanations

    positive descriptions and evaluations of individuals or services

    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
    lesia
    -0.07
    bable
    -0.07
    виÑī
    -0.07
     سÙħت
    -0.07
    ÑĦоÑĢми
    -0.07
    URLException
    -0.07
     ruku
    -0.07
    isclosed
    -0.06
    fo
    -0.06
    hea
    -0.06
    POSITIVE LOGITS
     my
    0.06
     ou
    0.06
    esson
    0.06
    ekk
    0.06
    mts
    0.06
     hands
    0.06
     an
    0.06
     ore
    0.06
    CUS
    0.06
    orz
    0.06
    Activations Density 0.029%

    No Known Activations