© 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. 15679
    Prev
    Next
    INDEX
    Explanations

    creative expressions related to emotional themes and storytelling

    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
     mastur
    -0.07
    (åľŁ
    -0.07
    RuleContext
    -0.07
    iationException
    -0.06
     jadx
    -0.06
    ÙģÙĤ
    -0.06
    celed
    -0.06
    aura
    -0.06
    .apiUrl
    -0.06
    دد
    -0.06
    POSITIVE LOGITS
    oko
    0.07
    ª
    0.07
    imiters
    0.06
    zyst
    0.06
    endant
    0.06
    iÃŁ
    0.06
     exercise
    0.06
    ort
    0.06
    blings
    0.06
     complication
    0.06
    Activations Density 0.037%

    No Known Activations