© 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. 107946
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to functions and methods

    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
    ugin
    -0.09
    å²Ĺ
    -0.09
    _ASSUME
    -0.09
    edBy
    -0.08
    å»Ĭ
    -0.08
    _EXTERN
    -0.08
     Kemal
    -0.08
    onas
    -0.08
    diler
    -0.08
    viÄį
    -0.08
    POSITIVE LOGITS
    anon
    0.07
     Anonymous
    0.07
     autogenerated
    0.07
     unnamed
    0.06
    0.06
     anonymous
    0.06
     unde
    0.05
     internal
    0.05
     class
    0.05
     bi
    0.05
    Activations Density 0.001%

    No Known Activations