© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 57353
    Prev
    Next
    INDEX
    Explanations

    HTML metadata tags

    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
    -thumbnails
    -0.08
    ansi
    -0.08
    Enumeration
    -0.07
    ŀĭ
    -0.07
    çı
    -0.07
     завÑĤÑĢа
    -0.07
    BorderStyle
    -0.07
    pes
    -0.07
    afd
    -0.07
    SCII
    -0.07
    POSITIVE LOGITS
    za
    0.06
     Favor
    0.05
     Nob
    0.05
    ibraltar
    0.05
     Expl
    0.05
     Trio
    0.05
    readcr
    0.05
     Yao
    0.05
     Lear
    0.05
     tier
    0.05
    Activations Density 0.001%

    No Known Activations