© 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. 5650
    Prev
    Next
    INDEX
    Explanations

    technical terms related to physical shapes and configurations in a scientific context

    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
    elize
    -0.08
    teg
    -0.07
    Ïģαν
    -0.06
    æķ·
    -0.06
    .inline
    -0.06
    inet
    -0.06
    _TRAIN
    -0.06
    etat
    -0.06
    ValuePair
    -0.06
    że
    -0.06
    POSITIVE LOGITS
     represented
    0.17
    represented
    0.16
     via
    0.12
    via
    0.11
     expressed
    0.09
    Via
    0.09
     Via
    0.08
     bằng
    0.08
     measured
    0.08
    _via
    0.08
    Activations Density 0.113%

    No Known Activations