© 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. 57945
    Prev
    Next
    INDEX
    Explanations

    words that indicate the origin or source of concepts

    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
    eyh
    -0.07
    ÑĪиÑĢ
    -0.07
    alle
    -0.07
    aran
    -0.07
    ba
    -0.07
    uw
    -0.06
    ALLE
    -0.06
    alar
    -0.06
     Firm
    -0.06
    istas
    -0.06
    POSITIVE LOGITS
     from
    0.07
    igsaw
    0.07
    gers
    0.07
    CHAT
    0.07
    áž
    0.07
    adt
    0.07
    ALLY
    0.06
     ÑģобоÑİ
    0.06
    IGNAL
    0.06
    FromClass
    0.06
    Activations Density 0.007%

    No Known Activations