© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126889
    Prev
    Next
    INDEX
    Explanations

    references to specific animal species and their characteristics

    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
    illage
    -0.07
    ãĥ³ãĥIJ
    -0.07
    rieben
    -0.06
     Wheels
    -0.06
     Dumpster
    -0.06
     Hyde
    -0.06
     Beste
    -0.06
     diffs
    -0.06
     Pace
    -0.05
     unfit
    -0.05
    POSITIVE LOGITS
    asca
    0.07
    GINE
    0.07
    /ic
    0.07
    anine
    0.06
    ath
    0.06
    tsky
    0.06
    adlo
    0.06
    Segue
    0.06
    ads
    0.06
    SION
    0.06
    Activations Density 0.006%

    No Known Activations