© 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 EvalsExportsinterp-engineNEWAPI 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. 73520
    Prev
    Next
    INDEX
    Explanations

    terms related to symbols and symbolic language

    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
    erman
    -0.08
    ĮĢ
    -0.08
    ิà¸ŀ
    -0.08
    liness
    -0.07
    aus
    -0.07
    isman
    -0.07
    ster
    -0.07
    comb
    -0.07
    esy
    -0.07
    eras
    -0.07
    POSITIVE LOGITS
    /sign
    0.09
    osate
    0.09
    urai
    0.08
    son
    0.08
    lico
    0.07
    mith
    0.07
    .fi
    0.07
    izont
    0.07
    ized
    0.07
    ëł¹
    0.07
    Activations Density 0.015%

    No Known Activations