© 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. 126685
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a suggestion or recommendation

    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
    assis
    -0.07
    :uint
    -0.07
    avis
    -0.07
    ãģĤãģĴ
    -0.07
    umer
    -0.07
    quist
    -0.07
    ats
    -0.07
    itler
    -0.07
    azon
    -0.06
    aeda
    -0.06
    POSITIVE LOGITS
     that
    0.10
     rằng
    0.10
    ively
    0.09
     perhaps
    0.07
    ors
    0.07
    that
    0.07
    oul
    0.07
     Ñģобой
    0.06
     rather
    0.06
     there
    0.06
    Activations Density 0.013%

    No Known Activations