© 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. 14628
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

    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
     Bulk
    -0.07
    aign
    -0.06
     rew
    -0.06
    rection
    -0.06
     corre
    -0.06
     Äiji
    -0.06
     Clarkson
    -0.06
    esel
    -0.06
     corrid
    -0.06
     Barack
    -0.06
    POSITIVE LOGITS
    erland
    0.07
     Sac
    0.06
    usercontent
    0.06
    Globals
    0.06
    ixer
    0.06
    omanip
    0.06
    isman
    0.06
     Fon
    0.06
     Buen
    0.06
     Fat
    0.06
    Activations Density 0.005%

    No Known Activations