© 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. 1967
    Prev
    Next
    INDEX
    Explanations

    references to sound and auditory imagery

    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
    ennon
    -0.07
    ÑĥÑħ
    -0.07
    imity
    -0.06
    369
    -0.06
    etro
    -0.06
    odor
    -0.06
     sense
    -0.06
    лав
    -0.06
    owe
    -0.06
     ima
    -0.06
    POSITIVE LOGITS
     Thornton
    0.06
     zám
    0.06
    preter
    0.06
    itan
    0.06
    K
    0.06
     Carroll
    0.06
    477
    0.06
    802
    0.06
     Pruitt
    0.06
    473
    0.06
    Activations Density 0.011%

    No Known Activations