© 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. 74539
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or programming elements

    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
    ivor
    -0.08
    ublik
    -0.07
    requestData
    -0.06
    ύ
    -0.06
    apollo
    -0.06
    ÑģлÑĸд
    -0.06
    ixon
    -0.06
    ouch
    -0.06
    icens
    -0.06
    unami
    -0.06
    POSITIVE LOGITS
    actionDate
    0.08
     mát
    0.07
     baÅŁta
    0.07
    iParam
    0.06
     trÃŃ
    0.06
     окÑĢÑĥж
    0.06
    ÅĻÃŃt
    0.06
    (éĩij
    0.06
    볨
    0.06
     daleko
    0.06
    Activations Density 2.035%

    No Known Activations