© 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. 85012
    Prev
    Next
    INDEX
    Explanations

    statements and expressions of opinion or emotions

    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
    ">//
    -0.07
    ignet
    -0.07
     ÑĤÑĥÑĤ
    -0.07
    .Footer
    -0.07
    epend
    -0.06
     ìĹ¬ê¸°
    -0.06
    á»ĵn
    -0.06
     serbest
    -0.06
    .sap
    -0.06
    556
    -0.06
    POSITIVE LOGITS
    ilon
    0.07
     basically
    0.06
     how
    0.06
     essentially
    0.06
    gia
    0.06
    :↵
    0.06
     ent
    0.06
    :
    0.06
     briefly
    0.06
     details
    0.06
    Activations Density 0.044%

    No Known Activations