© 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. 39234
    Prev
    Next
    INDEX
    Explanations

    auditory imagery and sounds

    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
    hani
    -0.07
    enda
    -0.07
    -definition
    -0.06
     plugged
    -0.06
     plug
    -0.06
    tube
    -0.06
    plug
    -0.06
    .sm
    -0.06
    corp
    -0.06
    oplevel
    -0.06
    POSITIVE LOGITS
    çİĩ
    0.07
    ety
    0.07
    ity
    0.07
    -click
    0.07
    ÏĥÏĦο
    0.07
    åĵį
    0.07
    (click
    0.06
    /flutter
    0.06
    /cl
    0.06
    713
    0.06
    Activations Density 0.020%

    No Known Activations