© 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. 95377
    Prev
    Next
    INDEX
    Explanations

    expressions related to official announcements or statements

    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
    SION
    -0.07
    panse
    -0.07
    avia
    -0.06
    edium
    -0.06
    impse
    -0.06
    resh
    -0.06
    env
    -0.06
    ilio
    -0.06
    arket
    -0.06
    icos
    -0.06
    POSITIVE LOGITS
     press
    0.08
    statement
    0.07
     statement
    0.06
    Aligned
    0.06
    azers
    0.06
     Boyd
    0.06
    vsp
    0.06
     release
    0.06
    utch
    0.06
    chwitz
    0.06
    Activations Density 0.006%

    No Known Activations