© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80490
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or singular focus

    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
    ensa
    -0.06
     quite
    -0.06
    çĦ¶
    -0.06
    lose
    -0.06
    tt
    -0.06
    .Fetch
    -0.06
    462
    -0.06
    ters
    -0.06
     sic
    -0.06
    tÃŃ
    -0.06
    POSITIVE LOGITS
    upy
    0.07
    omy
    0.07
    za
    0.06
    ibi
    0.06
    imus
    0.06
     crises
    0.06
    jes
    0.06
    .docker
    0.06
    jack
    0.06
    OrDefault
    0.06
    Activations Density 0.026%

    No Known Activations