© 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. 120167
    Prev
    Next
    INDEX
    Explanations

    details related to statistics and achievements over time

    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
     im
    -0.06
    ź
    -0.05
     o
    -0.05
     Kot
    -0.05
    ory
    -0.05
    âĢ¦↵
    -0.05
     sw
    -0.05
    μβ
    -0.05
     Colbert
    -0.05
     Consumers
    -0.05
    POSITIVE LOGITS
    ailles
    0.08
    adiens
    0.08
    ÑĢив
    0.08
    amilia
    0.08
    visitor
    0.08
    _visitor
    0.08
    turnstile
    0.08
    apore
    0.08
    olare
    0.08
    geh
    0.08
    Activations Density 0.003%

    No Known Activations