© 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. 89876
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    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
    ASTE
    -0.06
     GS
    -0.06
    FRING
    -0.06
    masters
    -0.05
    CAST
    -0.05
    anmar
    -0.05
    -AA
    -0.05
    iddleware
    -0.05
     kern
    -0.05
    istar
    -0.05
    POSITIVE LOGITS
    wine
    0.07
    dek
    0.07
    ùi
    0.06
    sko
    0.06
    rlen
    0.06
    lee
    0.06
    ORG
    0.06
    atu
    0.06
    ıf
    0.06
    ek
    0.06
    Activations Density 0.004%

    No Known Activations