© 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. 15-LLAMASCOPE-RES-131K
    6. 62529
    Prev
    Next
    INDEX
    Explanations

    comparisons and similes used to describe people or situations

    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
    iface
    -0.07
    ugin
    -0.07
    ikk
    -0.07
    Ñİн
    -0.07
    æģ¯
    -0.06
    irl
    -0.06
    áÄį
    -0.06
    iva
    -0.06
    ikan
    -0.06
    builtin
    -0.06
    POSITIVE LOGITS
     бÑĥдÑĤо
    0.09
     somehow
    0.08
    odata
    0.06
     chy
    0.06
     consum
    0.06
    ä¼¼çļĦ
    0.06
    zier
    0.06
    нез
    0.06
    ritis
    0.06
    _MAGIC
    0.06
    Activations Density 0.022%

    No Known Activations