© 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. 30542
    Prev
    Next
    INDEX
    Explanations

    technical terms related to graph structures and programming frameworks

    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
    rgan
    -0.07
    (s
    -0.07
     organisation
    -0.06
    arger
    -0.06
    oft
    -0.06
    arih
    -0.06
    ãģĶ
    -0.06
    sth
    -0.06
     Neg
    -0.06
    Pie
    -0.06
    POSITIVE LOGITS
    mojom
    0.07
    .gwt
    0.07
    .mapbox
    0.07
    onest
    0.07
    ASSES
    0.07
     CASCADE
    0.07
    IGNAL
    0.06
    adi
    0.06
    uges
    0.06
    icom
    0.06
    Activations Density 0.008%

    No Known Activations