© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71783
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific programming language syntax

    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
    .scalablytyped
    -0.07
    ouve
    -0.07
    arden
    -0.07
    iber
    -0.07
     situaci
    -0.06
    loven
    -0.06
    .Logging
    -0.06
    auen
    -0.06
     Seks
    -0.06
     wedge
    -0.06
    POSITIVE LOGITS
    Ìģt
    0.08
    eras
    0.06
    )prepare
    0.06
    ÑĢиÑģ
    0.06
    eric
    0.06
    apons
    0.06
     sav
    0.06
    åħĦ
    0.06
    ÎŃ
    0.06
    abe
    0.06
    Activations Density 0.000%

    No Known Activations