© 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. 105047
    Prev
    Next
    INDEX
    Explanations

    instances of causation or attribution in descriptions

    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
    .scalablytyped
    -0.07
    ->__
    -0.06
    æĿ
    -0.06
     til
    -0.06
    allas
    -0.06
    anka
    -0.05
    75
    -0.05
    Compiled
    -0.05
    /inc
    -0.05
     essentially
    -0.05
    POSITIVE LOGITS
    letcher
    0.08
     mater
    0.07
    strup
    0.07
    bilder
    0.07
    .si
    0.07
    oreach
    0.07
    wap
    0.07
    teg
    0.07
     SavaÅŁ
    0.07
    _IDENT
    0.06
    Activations Density 0.000%

    No Known Activations