© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 83881
    Prev
    Next
    INDEX
    Explanations

    mentions of the character Rudolph or related variations

    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
    iard
    -0.08
    rieb
    -0.07
    alez
    -0.07
    erland
    -0.07
    buie
    -0.07
    ãĥ³ãĤ°
    -0.06
    nist
    -0.06
    ean
    -0.06
    AGES
    -0.06
     Ø°Ùĩ
    -0.06
    POSITIVE LOGITS
    amel
    0.09
    olph
    0.09
    imentary
    0.08
    gers
    0.07
    usal
    0.07
    ger
    0.06
     SpoleÄį
    0.06
    geme
    0.06
     Lesser
    0.06
    Ùij
    0.06
    Activations Density 0.005%

    No Known Activations