© 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. 15-LLAMASCOPE-RES-131K
    11. 90640
    Prev
    Next
    INDEX
    Explanations

    statements or phrases discussing challenges and their implications

    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
    aea
    -0.07
    UNE
    -0.07
    ae
    -0.07
    vise
    -0.07
    FFE
    -0.06
    rette
    -0.06
    ati
    -0.06
    GINE
    -0.06
    awe
    -0.06
    аÐ
    -0.06
    POSITIVE LOGITS
     ones
    0.07
    polator
    0.06
    eos
    0.06
     res
    0.06
    afari
    0.06
    .TryParse
    0.06
    ingroup
    0.06
    ÑĢÑĸÑĩ
    0.06
    _pcm
    0.06
    isque
    0.06
    Activations Density 0.169%

    No Known Activations