© 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. 31248
    Prev
    Next
    INDEX
    Explanations

    the word "TODAY" in a sports context

    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
    iffin
    -0.07
    itm
    -0.06
    è°ĥ
    -0.06
    Ñĸж
    -0.06
    elu
    -0.06
    ipo
    -0.06
    atalog
    -0.06
    vas
    -0.06
     Schwe
    -0.06
     FRE
    -0.06
    POSITIVE LOGITS
    oldt
    0.09
     discriminator
    0.06
    -scalable
    0.06
    illon
    0.06
    LOPT
    0.06
     ByVal
    0.06
     Ult
    0.06
    assi
    0.06
     Pun
    0.06
     Grat
    0.06
    Activations Density 0.001%

    No Known Activations