© 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. 85646
    Prev
    Next
    INDEX
    Explanations

    strings or sections that contain non-English characters or foreign language content

    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
    roit
    -0.08
    mav
    -0.07
    uitka
    -0.07
    olvency
    -0.07
    dsa
    -0.07
    riteria
    -0.07
    ãi
    -0.07
    ossier
    -0.07
    dra
    -0.07
    ´
    -0.06
    POSITIVE LOGITS
    Dash
    0.06
     Malk
    0.06
    ymph
    0.06
     Mez
    0.06
     Christoph
    0.06
    inker
    0.06
     dash
    0.06
    ilit
    0.06
    ash
    0.06
    öyle
    0.06
    Activations Density 0.000%

    No Known Activations