© 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. 15-LLAMASCOPE-RES-131K
    6. 1217
    Prev
    Next
    INDEX
    Explanations

    terms related to gatherings or discussions

    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
    ñana
    -0.07
    kola
    -0.07
    itoris
    -0.07
    acey
    -0.07
    bakan
    -0.07
    usta
    -0.07
    ưng
    -0.07
     YELLOW
    -0.07
    eldom
    -0.07
    üs
    -0.07
    POSITIVE LOGITS
     at
    0.07
    recent
    0.05
     recent
    0.05
     Lind
    0.05
     titled
    0.05
     Rai
    0.05
    anti
    0.05
     Baba
    0.05
     where
    0.05
     fellow
    0.05
    Activations Density 0.023%

    No Known Activations