© 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 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. 17-LLAMASCOPE-RES-131K
    11. 85788
    Prev
    Next
    INDEX
    Explanations

    references to previous posts and articles

    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
    éĢģæĸĻçĦ¡æĸĻ
    -0.08
    ansk
    -0.07
    GF
    -0.07
    ens
    -0.07
    باÙĨ
    -0.06
     @@↵
    -0.06
    erate
    -0.06
    .INSTANCE
    -0.06
    otate
    -0.06
    ungs
    -0.06
    POSITIVE LOGITS
     titled
    0.09
     entitled
    0.09
    .scalablytyped
    0.07
     devoted
    0.07
     Burr
    0.07
     dedicated
    0.07
    TOT
    0.07
    upal
    0.07
    ssql
    0.06
     pac
    0.06
    Activations Density 0.015%

    No Known Activations