© 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. 77246
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as classes and methods

    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
    avenport
    -0.07
    ebra
    -0.07
    sv
    -0.07
    eryl
    -0.07
    Äįi
    -0.06
    annel
    -0.06
    ograd
    -0.06
     roz
    -0.06
    lette
    -0.06
    ebe
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    дн
    0.07
     FUNCT
    0.07
     public
    0.07
    asher
    0.06
    _cmos
    0.06
    оказ
    0.06
    .ReadString
    0.06
    .GetAxis
    0.06
    *>*
    0.06
    Activations Density 0.027%

    No Known Activations