© 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. 61489
    Prev
    Next
    INDEX
    Explanations

    emphasis on the word "just."

    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
    098
    -0.06
    ALLE
    -0.06
     Hud
    -0.06
    åıİ
    -0.06
    887
    -0.06
    ãģ¸ãģ¨
    -0.06
    avar
    -0.06
    Upon
    -0.06
     upon
    -0.06
    omba
    -0.06
    POSITIVE LOGITS
    edith
    0.07
     INCIDENT
    0.07
    ãģĺ
    0.07
     _{}
    0.07
    .Clone
    0.06
     kaps
    0.06
    mite
    0.06
    elt
    0.06
    ábado
    0.06
    .handlers
    0.06
    Activations Density 0.000%

    No Known Activations