© 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. 124105
    Prev
    Next
    INDEX
    Explanations

    URLs and web-related content

    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
    engo
    -0.06
     good
    -0.06
    romium
    -0.05
    igo
    -0.05
    unkt
    -0.05
    roadcast
    -0.05
     Wikimedia
    -0.05
     #
    -0.05
     step
    -0.05
     Ken
    -0.05
    POSITIVE LOGITS
    ENE
    0.08
    .story
    0.08
    /story
    0.08
    楽ãģĹ
    0.07
    _story
    0.07
    Story
    0.07
    UPI
    0.07
    sterol
    0.07
    iggins
    0.07
    illos
    0.07
    Activations Density 0.018%

    No Known Activations