© 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. 119302
    Prev
    Next
    INDEX
    Explanations

    verbs related to capability and potential

    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
    nez
    -0.07
    ίÏĥ
    -0.07
    ucch
    -0.06
    ÑģÑĤвоÑĢ
    -0.06
    oure
    -0.06
    chio
    -0.06
    oston
    -0.06
    esco
    -0.06
    odos
    -0.06
    WW
    -0.06
    POSITIVE LOGITS
    leftright
    0.07
    aren
    0.07
    caler
    0.07
    ãĥĨãĥ«
    0.07
    aben
    0.06
    ãĥ¼ãĥĵ
    0.06
    etched
    0.06
    677
    0.06
    زÙħ
    0.06
    anvas
    0.06
    Activations Density 0.003%

    No Known Activations