© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 59784
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the significance and roles of libraries and public spaces in communities

    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
     tÃŃm
    -0.07
    aset
    -0.07
    ieres
    -0.07
    HEMA
    -0.07
     positional
    -0.06
    ÐĿÐŀ
    -0.06
     carried
    -0.06
    avou
    -0.06
     ç¯
    -0.06
    avo
    -0.06
    POSITIVE LOGITS
     place
    0.15
     places
    0.12
     where
    0.12
     nơi
    0.11
    çļĦåľ°æĸ¹
    0.11
    place
    0.11
     location
    0.10
     site
    0.10
     меÑģÑĤо
    0.10
     venue
    0.10
    Activations Density 0.085%

    No Known Activations