© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 77273
    Prev
    Next
    INDEX
    Explanations

    references to the word "Burn" and its variations

    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
    licit
    -0.08
    ditor
    -0.07
    θε
    -0.07
    åİħ
    -0.07
    anford
    -0.07
    gger
    -0.07
    ually
    -0.07
    uale
    -0.07
    ulin
    -0.06
    quare
    -0.06
    POSITIVE LOGITS
    outs
    0.08
    ishing
    0.08
    ished
    0.08
     ðŁĶ
    0.07
    out
    0.07
    side
    0.07
    away
    0.07
     Lazar
    0.07
    çĩ
    0.07
    iece
    0.07
    Activations Density 0.013%

    No Known Activations