© 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. 5-LLAMASCOPE-RES-131K
    6. 125668
    Prev
    Next
    INDEX
    Explanations

    references to instances of fire or burning events

    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
    dee
    -0.06
    ivering
    -0.06
    æ¨
    -0.06
    riterion
    -0.06
    argent
    -0.06
    rees
    -0.06
    .gb
    -0.06
    Ù쨧ÙĦ
    -0.06
    inci
    -0.06
    pillar
    -0.06
    POSITIVE LOGITS
    erek
    0.06
    amam
    0.06
    uma
    0.06
    onders
    0.06
    IGHT
    0.06
    849
    0.06
    ucene
    0.06
    igham
    0.06
    éłĨ
    0.06
    erge
    0.06
    Activations Density 0.003%

    No Known Activations