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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103169
    Prev
    Next
    INDEX
    Explanations

    key details related to upcoming events and announcements

    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
     ----------------------------------------------------------------------------↵
    -0.10
    'gc
    -0.09
     nues
    -0.09
     bacheca
    -0.08
     zdrav
    -0.08
     weiber
    -0.08
    εÏģγ
    -0.08
     ---------------------------------------------------------------------------↵
    -0.08
    (AT
    -0.08
     ragaz
    -0.08
    POSITIVE LOGITS
    0.08
     precisely
    0.07
     -
    0.06
     â
    0.06
     "
    0.06
    Âł
    0.06
     ke
    0.06
     personally
    0.06
     iron
    0.05
     exactly
    0.05
    Activations Density 0.007%

    No Known Activations