© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98873
    Prev
    Next
    INDEX
    Explanations

    XML parameter attributes

    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
    pha
    -0.06
    lena
    -0.06
    DED
    -0.06
    ingham
    -0.06
    achuset
    -0.06
    elia
    -0.05
    b
    -0.05
     phenomen
    -0.05
     maximum
    -0.05
    f
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.07
    eshire
    0.07
    ıkl
    0.07
    adaki
    0.07
     purch
    0.07
    klady
    0.07
    азв
    0.07
    annels
    0.06
    ©
    0.06
     excer
    0.06
    Activations Density 0.004%

    No Known Activations