© 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. 9-LLAMASCOPE-RES-131K
    11. 98263
    Prev
    Next
    INDEX
    Explanations

    chemical ingredients and formulations

    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
    lyn
    -0.06
     h
    -0.06
     Noel
    -0.06
    erais
    -0.06
     inv
    -0.06
    187
    -0.06
    assador
    -0.05
    ë¶ĦìĦĿ
    -0.05
     Holl
    -0.05
     ern
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
    ushi
    0.07
    eyen
    0.07
    oria
    0.07
    ëĵĿ
    0.06
    etus
    0.06
    rength
    0.06
    isan
    0.06
    /Area
    0.06
     EQUAL
    0.06
    Activations Density 0.003%

    No Known Activations