© 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. 78421
    Prev
    Next
    INDEX
    Explanations

    parts of the text related to groups, collections, or categories

    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
    hai
    -0.07
     such
    -0.07
    illions
    -0.07
    303
    -0.06
     flere
    -0.06
     elsewhere
    -0.06
     orm
    -0.06
    ÑģÑĮ
    -0.06
    758
    -0.06
     direction
    -0.06
    POSITIVE LOGITS
    vette
    0.08
    ä¹ĭä¸Ģ
    0.07
    -plus
    0.07
    uito
    0.07
     плÑİ
    0.07
    thouse
    0.07
    à¹ģรà¸ģ
    0.07
     plus
    0.07
    apore
    0.06
    idget
    0.06
    Activations Density 0.052%

    No Known Activations