© 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. 95350
    Prev
    Next
    INDEX
    Explanations

    financial terms and references to performance metrics

    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
     something
    -0.06
    ÑİÑģÑĮ
    -0.06
     perhaps
    -0.06
     even
    -0.06
     surprisingly
    -0.06
     probably
    -0.06
     Scar
    -0.06
     Shemale
    -0.06
    171
    -0.06
     again
    -0.06
    POSITIVE LOGITS
    |#
    0.07
    .Please
    0.07
    HEST
    0.07
     DCHECK
    0.07
    @js
    0.07
    &#
    0.07
    fak
    0.07
    please
    0.07
    ogle
    0.06
    ült
    0.06
    Activations Density 0.024%

    No Known Activations