© 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. 124864
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation used in formatting or notation

    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
    uff
    -0.07
    æľ¬å½ĵ
    -0.07
    uffs
    -0.07
    quares
    -0.07
    η
    -0.07
    ãĥ³ãĥĩãĤ£
    -0.07
    omatic
    -0.07
    _INFORMATION
    -0.07
    ENAME
    -0.07
    /compiler
    -0.07
    POSITIVE LOGITS
    nyder
    0.06
    addOn
    0.06
    urances
    0.06
     Micha
    0.06
    inati
    0.06
    aliz
    0.06
    ½
    0.06
     konkrét
    0.06
    cheng
    0.06
     scopes
    0.06
    Activations Density 0.003%

    No Known Activations