© 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. 81364
    Prev
    Next
    INDEX
    Explanations

    references to posts and posting activities

    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
    ously
    -0.09
    fast
    -0.08
    ìĹŃ
    -0.07
    zelf
    -0.07
    olds
    -0.06
    izer
    -0.06
    lect
    -0.06
    rvine
    -0.06
    ktop
    -0.06
    stakes
    -0.06
    POSITIVE LOGITS
    natal
    0.14
    erior
    0.12
    graduate
    0.12
    greSQL
    0.10
    gresql
    0.10
    cards
    0.10
    ulate
    0.09
    mort
    0.09
    uring
    0.09
     facto
    0.09
    Activations Density 0.038%

    No Known Activations