© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125230
    Prev
    Next
    INDEX
    Explanations

    references to authors or contributors of written works

    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
    Å¡t
    -0.06
    et
    -0.06
    áy
    -0.06
    0
    -0.06
    anel
    -0.06
    ucci
    -0.06
    ÑĩиÑĤ
    -0.06
    ierz
    -0.06
    .ping
    -0.06
    ander
    -0.05
    POSITIVE LOGITS
    oulos
    0.08
    olet
    0.07
    decltype
    0.07
    ãĥ³ãĥĦ
    0.07
    trl
    0.07
     Dr
    0.07
    isi
    0.07
    isia
    0.07
    llib
    0.07
    uthor
    0.07
    Activations Density 0.020%

    No Known Activations