© 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. 130682
    Prev
    Next
    INDEX
    Explanations

    numerical or coded information

    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
    oeff
    -0.08
    lify
    -0.08
    uish
    -0.07
    imers
    -0.07
    Feels
    -0.07
    etch
    -0.07
    META
    -0.07
    okol
    -0.07
    argo
    -0.07
    reff
    -0.07
    POSITIVE LOGITS
     Ra
    0.06
    Ra
    0.06
     Bros
    0.05
     çķ
    0.05
     sustain
    0.05
    (disposing
    0.05
     Nos
    0.05
    aday
    0.05
     Maher
    0.05
     fore
    0.05
    Activations Density 0.000%

    No Known Activations