© 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. 22-LLAMASCOPE-RES-131K
    11. 3768
    Prev
    Next
    INDEX
    Explanations

    geographic features and formations in landscapes

    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
    _TRACE
    -0.06
     Shore
    -0.06
    ounder
    -0.06
     Demonstr
    -0.06
    ngine
    -0.06
    lland
    -0.06
    /help
    -0.06
    ardin
    -0.06
     PLUS
    -0.06
    еÑģÑĤÑĮ
    -0.06
    POSITIVE LOGITS
    rising
    0.08
     heights
    0.08
     rise
    0.08
     formations
    0.08
    rise
    0.08
     formation
    0.08
    -rise
    0.08
     height
    0.07
     Cloth
    0.07
     rising
    0.07
    Activations Density 0.030%

    No Known Activations