© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55579
    Prev
    Next
    INDEX
    Explanations

    references to API connections and remote interactions in technical contexts

    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
    (MenuItem
    -0.06
    .createFrom
    -0.06
    auer
    -0.06
    gere
    -0.06
     Sahara
    -0.06
    antine
    -0.06
     mechanic
    -0.06
    寧
    -0.06
     §§
    -0.06
     Alman
    -0.06
    POSITIVE LOGITS
     server
    0.10
     servers
    0.09
    æľįåĬ¡åύ
    0.09
    server
    0.08
     distant
    0.08
     ÑģеÑĢвеÑĢ
    0.08
    servers
    0.08
     ìĦľë²Ħ
    0.08
    _server
    0.07
    -server
    0.07
    Activations Density 0.038%

    No Known Activations