© 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. 38524
    Prev
    Next
    INDEX
    Explanations

    frequent punctuation marks and sentence enders

    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
    xz
    -0.07
    angu
    -0.07
    æŀľ
    -0.07
    CLU
    -0.07
    avigate
    -0.06
    κοÏĤ
    -0.06
    engu
    -0.06
    ocrates
    -0.06
    LLL
    -0.06
    å³
    -0.06
    POSITIVE LOGITS
    ONUS
    0.09
    Lastly
    0.08
     these
    0.08
     Lastly
    0.08
    以ä¸Ĭ
    0.08
     기íĥĢ
    0.07
    Bonus
    0.07
     These
    0.07
    these
    0.07
     Miscellaneous
    0.07
    Activations Density 0.005%

    No Known Activations