© 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. 17674
    Prev
    Next
    INDEX
    Explanations

    enthusiastic expressions and identifiers for creative works

    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
    opia
    -0.06
     Meghan
    -0.06
     Walt
    -0.06
     CN
    -0.05
    Ì
    -0.05
    eren
    -0.05
     Attachment
    -0.05
     ICC
    -0.05
     refin
    -0.05
    icit
    -0.05
    POSITIVE LOGITS
    Exited
    0.09
    à¸Ńส
    0.07
     BOOT
    0.07
    BOOT
    0.07
    alsex
    0.07
     cult
    0.07
    trl
    0.07
    mrt
    0.07
    á»·
    0.07
    éĤ¦
    0.07
    Activations Density 0.000%

    No Known Activations