© 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 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. 58758
    Prev
    Next
    INDEX
    Explanations

    sequential numerical indicators or labels in contexts involving classification or ranking

    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
     respectively
    -0.06
     “
    -0.06
     indeed
    -0.06
     gratuiti
    -0.06
     respective
    -0.06
     Triple
    -0.06
    utherford
    -0.05
     triple
    -0.05
    eslint
    -0.05
    ÅĻad
    -0.05
    POSITIVE LOGITS
     naopak
    0.08
    erse
    0.07
    795
    0.07
     ìĹŃìĭľ
    0.07
    231
    0.07
     dit
    0.07
     ones
    0.07
    ONES
    0.07
    adlo
    0.07
     же
    0.07
    Activations Density 0.022%

    No Known Activations