© 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. 69614
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and methods related to data structures and functions

    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
    cak
    -0.07
    ested
    -0.07
    peria
    -0.06
    aar
    -0.06
    ecz
    -0.06
    enser
    -0.06
    pcf
    -0.06
    รà¸ģ
    -0.06
    åĢį
    -0.06
    omik
    -0.06
    POSITIVE LOGITS
     [=
    0.09
     your
    0.07
    iscard
    0.06
    (IService
    0.06
    ÅĤad
    0.06
    your
    0.06
    .Slf
    0.06
    racat
    0.06
     ili
    0.06
    erland
    0.06
    Activations Density 0.025%

    No Known Activations