© 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. 29904
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming structures and variables

    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
    uji
    -0.08
    รม
    -0.07
    atta
    -0.07
    abay
    -0.07
    aeda
    -0.07
    onn
    -0.07
     nhau
    -0.07
    rhs
    -0.07
    edy
    -0.07
    ipa
    -0.07
    POSITIVE LOGITS
    樹
    0.07
    ).__
    0.07
     =
    0.06
    ÑĪев
    0.06
     Manip
    0.06
     purse
    0.06
    енз
    0.06
     Overs
    0.06
    ##_
    0.06
     Coat
    0.05
    Activations Density 0.033%

    No Known Activations