© 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. 15-LLAMASCOPE-RES-131K
    11. 27380
    Prev
    Next
    INDEX
    Explanations

    numerical references and categorizations related to scientific or statistical content

    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
    ester
    -0.07
    á»įc
    -0.07
    INT
    -0.06
     Pel
    -0.06
     Cadillac
    -0.05
     Uncle
    -0.05
    559
    -0.05
    osing
    -0.05
     uncertain
    -0.05
    489
    -0.05
    POSITIVE LOGITS
     нанеÑģ
    0.08
    ضÙĬ
    0.08
    گز
    0.07
    anine
    0.07
    .SIG
    0.07
    amik
    0.07
    Äĥm
    0.07
    rouw
    0.07
    .blit
    0.07
     tactile
    0.07
    Activations Density 0.006%

    No Known Activations