© 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. 125680
    Prev
    Next
    INDEX
    Explanations

    mentions of the platform GitHub

    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
     seedu
    -0.06
    æį
    -0.06
     Howe
    -0.06
    .Pointer
    -0.06
     Clifford
    -0.06
     Germans
    -0.06
    hel
    -0.06
     _{}
    -0.06
    .Geometry
    -0.06
    gel
    -0.06
    POSITIVE LOGITS
    rades
    0.08
    oss
    0.07
    cosa
    0.07
    \OptionsResolver
    0.07
    ymes
    0.07
     contributor
    0.07
    edin
    0.07
    ida
    0.06
    UGIN
    0.06
    agger
    0.06
    Activations Density 0.002%

    No Known Activations