© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95298
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of infection

    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
    veau
    -0.08
    erner
    -0.08
    .metro
    -0.08
    é¡į
    -0.07
     konz
    -0.07
    ırak
    -0.07
    é®®
    -0.07
    éī
    -0.07
     bergen
    -0.07
    anken
    -0.07
    POSITIVE LOGITS
     nut
    0.06
    iform
    0.06
     Ju
    0.06
     form
    0.05
     Gat
    0.05
    kud
    0.05
    nut
    0.05
    olars
    0.05
    ch
    0.05
     rein
    0.05
    Activations Density 0.000%

    No Known Activations