© 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. 1484
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to lighthouse construction and operation

    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
     antenn
    -0.06
    akis
    -0.06
     microwave
    -0.06
    celik
    -0.06
    ienes
    -0.06
    istrat
    -0.06
    meer
    -0.06
    ellipsis
    -0.06
     expressive
    -0.06
     Rally
    -0.06
    POSITIVE LOGITS
    ashboard
    0.07
    glass
    0.07
    ined
    0.07
     tehdy
    0.07
    æķ
    0.07
    inery
    0.07
    inand
    0.07
     contr
    0.06
    agraph
    0.06
    URATION
    0.06
    Activations Density 0.004%

    No Known Activations