© 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. 57884
    Prev
    Next
    INDEX
    Explanations

    scientific publication references and their associated details

    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
    ighth
    -0.08
    egas
    -0.08
    essim
    -0.07
     syscall
    -0.07
    eturn
    -0.07
    isz
    -0.07
    agu
    -0.06
    thur
    -0.06
     decom
    -0.06
    AGR
    -0.06
    POSITIVE LOGITS
    أس
    0.06
    yat
    0.06
     backward
    0.06
    à¥Ĥद
    0.06
    adel
    0.06
    æ²¹
    0.06
    soon
    0.06
    onto
    0.06
    951
    0.06
    950
    0.05
    Activations Density 0.040%

    No Known Activations