© 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. 58012
    Prev
    Next
    INDEX
    Explanations

    parenthetical references and encapsulations in text

    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
    eba
    -0.08
    ideographic
    -0.08
    mpr
    -0.07
    ascript
    -0.07
    uien
    -0.07
    Ñģен
    -0.07
    outu
    -0.07
    usercontent
    -0.07
    imest
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    POSITIVE LOGITS
    alin
    0.07
    ãģĿãĤĮ
    0.06
    kit
    0.06
    afe
    0.06
    820
    0.06
    av
    0.06
    aaS
    0.06
    Âł
    0.06
    762
    0.06
    865
    0.05
    Activations Density 0.014%

    No Known Activations