© 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. 17-LLAMASCOPE-RES-131K
    11. 74120
    Prev
    Next
    INDEX
    Explanations

    mentions of the Washington Post

    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
    ework
    -0.07
    orca
    -0.06
     Fle
    -0.06
    lue
    -0.06
     Relative
    -0.06
    icine
    -0.05
    _mgr
    -0.05
    rais
    -0.05
    _radi
    -0.05
    Specifier
    -0.05
    POSITIVE LOGITS
    樹
    0.07
    ην
    0.07
    ROP
    0.07
    LOPT
    0.07
    imler
    0.06
    меÑĤÑĮ
    0.06
     \`
    0.06
    /rules
    0.06
    /Framework
    0.06
    Ĭ
    0.06
    Activations Density 0.005%

    No Known Activations