© 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. 72010
    Prev
    Next
    INDEX
    Explanations

    specific references to governing bodies or policies

    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
    èĤ©
    -0.07
    elm
    -0.07
    853
    -0.07
    852
    -0.07
    asons
    -0.06
    isman
    -0.06
    )((((
    -0.06
    è¾ħ
    -0.06
     Clem
    -0.06
    oyer
    -0.06
    POSITIVE LOGITS
     solution
    0.14
     Solution
    0.12
    Solution
    0.11
    solution
    0.11
     best
    0.11
     option
    0.10
     way
    0.10
     easiest
    0.10
     Way
    0.09
    option
    0.09
    Activations Density 0.072%

    No Known Activations