© 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. 70458
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight surprising or lesser-known information

    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
    clr
    -0.06
    æŀ
    -0.06
    ãģ¡ãĤĩ
    -0.06
     czy
    -0.06
    Ã
    -0.06
    emer
    -0.06
     ç¸
    -0.06
    ÑĢап
    -0.06
    ault
    -0.06
    _helpers
    -0.06
    POSITIVE LOGITS
     facts
    0.07
    833
    0.07
     Eh
    0.07
     fact
    0.07
    aea
    0.06
    ائÙĤ
    0.06
    bies
    0.06
    aras
    0.06
    LogLevel
    0.06
    eker
    0.06
    Activations Density 0.003%

    No Known Activations