© 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. 14553
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions and phrases indicating partnerships or associations

    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
    geme
    -0.07
    ensi
    -0.07
     нед
    -0.07
    سر
    -0.07
    Ä±ÅŁÄ±
    -0.07
     kéo
    -0.07
    ãĥªãĤ«
    -0.07
    xcd
    -0.07
    uggy
    -0.07
    åıĬåħ¶
    -0.07
    POSITIVE LOGITS
     counting
    0.08
     multiple
    0.08
     two
    0.07
     several
    0.07
     thousands
    0.07
    inyin
    0.07
     three
    0.06
    acher
    0.06
     hundreds
    0.06
    ippo
    0.06
    Activations Density 0.016%

    No Known Activations