© 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. 58311
    Prev
    Next
    INDEX
    Explanations

    terms related to contests and sweepstakes

    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
    asan
    -0.07
    lament
    -0.07
    utures
    -0.07
    apas
    -0.06
     à¤Ĩà¤ķर
    -0.06
    alam
    -0.06
    -fontawesome
    -0.06
     rather
    -0.06
    entai
    -0.06
    tridges
    -0.06
    POSITIVE LOGITS
    ugas
    0.06
    IRM
    0.06
    éĢīæĭ
    0.06
    Ä±ÅŁÄ±k
    0.06
     aforementioned
    0.06
     drained
    0.06
    etermined
    0.06
    eln
    0.06
    /***/
    0.06
    caption
    0.05
    Activations Density 0.001%

    No Known Activations