© 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 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. 17-LLAMASCOPE-RES-131K
    11. 59104
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating failure or absence

    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
    ãĤıãģij
    -0.07
    beck
    -0.07
    eward
    -0.07
    apk
    -0.06
    annon
    -0.06
    aset
    -0.06
    ãĥªãĥ³
    -0.06
     >",
    -0.06
    DMIN
    -0.06
     suche
    -0.06
    POSITIVE LOGITS
     altogether
    0.07
    ź
    0.07
    gart
    0.07
     even
    0.06
     vůbec
    0.06
     initially
    0.06
     Consortium
    0.06
     originally
    0.06
    icorn
    0.06
     Proper
    0.06
    Activations Density 0.056%

    No Known Activations