© 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. 1410
    Prev
    Next
    INDEX
    Explanations

    material types used in products

    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
    chner
    -0.07
    hazi
    -0.06
    eut
    -0.06
    getResponse
    -0.06
    atak
    -0.06
    .à¸ŀ
    -0.06
     Gateway
    -0.06
    .bp
    -0.06
    oman
    -0.06
    ÑĦÑĸ
    -0.06
    POSITIVE LOGITS
     base
    0.07
     Blasio
    0.07
    icc
    0.07
    -base
    0.07
    å°¼äºļ
    0.07
    enderit
    0.06
    eci
    0.06
    à¸Ļว
    0.06
    .AppendFormat
    0.06
    -based
    0.06
    Activations Density 0.015%

    No Known Activations