© 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. 108395
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "on."

    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
    oler
    -0.06
    eck
    -0.06
    éļİ
    -0.06
     Feder
    -0.06
    ç¬Ķ
    -0.06
    çŃĨ
    -0.06
    æ··
    -0.06
     camer
    -0.06
    许
    -0.06
    "crypto
    -0.06
    POSITIVE LOGITS
     public
    0.08
     website
    0.08
     websites
    0.08
     online
    0.07
    website
    0.07
    illisecond
    0.07
     Public
    0.07
    elm
    0.07
    public
    0.07
     sites
    0.07
    Activations Density 0.019%

    No Known Activations