© 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. 57291
    Prev
    Next
    INDEX
    Explanations

    articles related to notable individuals and their accomplishments

    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
    ospel
    -0.08
     Hicks
    -0.08
    uib
    -0.08
    ~-
    -0.08
    -INFRINGEMENT
    -0.07
     cez
    -0.07
    ãĥ£
    -0.07
    ãģħ
    -0.07
    ạm
    -0.07
     åĥ
    -0.07
    POSITIVE LOGITS
     part
    0.08
    0.07
     on
    0.07
    -go
    0.06
     guest
    0.06
     go
    0.06
     guests
    0.06
     instrumental
    0.06
     participants
    0.06
     in
    0.06
    Activations Density 0.027%

    No Known Activations