© 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. 60966
    Prev
    Next
    INDEX
    Explanations

    references to programming frameworks and libraries

    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
    olini
    -0.08
    nown
    -0.07
    dra
    -0.07
    licken
    -0.06
    avo
    -0.06
    ilih
    -0.06
    akra
    -0.06
    itting
    -0.06
    andest
    -0.06
    hou
    -0.06
    POSITIVE LOGITS
    uen
    0.07
    axon
    0.07
    ãĥĭ
    0.06
    oman
    0.06
    elves
    0.06
    RM
    0.06
    rogen
    0.06
    ÐĽÑİ
    0.06
    cia
    0.06
     pitch
    0.06
    Activations Density 0.000%

    No Known Activations