© 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. 95139
    Prev
    Next
    INDEX
    Explanations

    references to loudness or volume

    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
    idar
    -0.07
    azio
    -0.07
    iles
    -0.07
    ools
    -0.07
    ooled
    -0.06
     大éĺª
    -0.06
    byt
    -0.06
    esar
    -0.06
    볨
    -0.06
    utures
    -0.06
    POSITIVE LOGITS
    speaker
    0.13
    spe
    0.10
    mouth
    0.09
    ness
    0.08
    lier
    0.08
    arde
    0.07
    -mouth
    0.07
    Enough
    0.07
    TEMPL
    0.07
    icrous
    0.07
    Activations Density 0.012%

    No Known Activations