© 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. 1474
    Prev
    Next
    INDEX
    Explanations

    references to virtual events and their accessibility

    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
     pit
    -0.07
    endant
    -0.06
    éĢ£
    -0.06
     scanners
    -0.05
     Abrams
    -0.05
     dut
    -0.05
    .ManyToMany
    -0.05
     fed
    -0.05
    pit
    -0.05
     bi
    -0.05
    POSITIVE LOGITS
     replay
    0.10
     archives
    0.10
     archive
    0.10
     Replay
    0.10
    _archive
    0.10
    archive
    0.10
     repl
    0.10
    archives
    0.09
     missed
    0.09
    -archive
    0.09
    Activations Density 0.033%

    No Known Activations