© 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. 38290
    Prev
    Next
    INDEX
    Explanations

    terms related to specific quantities and configurations in recipes or processes

    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
    agoon
    -0.07
    osti
    -0.07
    eyen
    -0.07
    ä¸Ķ
    -0.07
    amina
    -0.06
    essa
    -0.06
    aina
    -0.06
    ãģĿãģĹãģ¦
    -0.06
    ìķ¼
    -0.06
     Alternate
    -0.06
    POSITIVE LOGITS
     if
    0.13
     nếu
    0.10
     or
    0.09
    if
    0.09
    	if
    0.09
     jika
    0.09
     ÑıкÑīо
    0.09
     еÑģли
    0.09
     wenn
    0.08
     å¦Ĥæŀľ
    0.08
    Activations Density 0.126%

    No Known Activations