© 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. 73131
    Prev
    Next
    INDEX
    Explanations

    references to placement or indications of position in text

    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
    eldon
    -0.06
    каÑĤ
    -0.06
    ikit
    -0.06
    ervo
    -0.06
    å¡ļ
    -0.06
    andon
    -0.06
    adal
    -0.06
    erc
    -0.06
    umann
    -0.06
    ãĥĪãĥ«
    -0.06
    POSITIVE LOGITS
     CreateMap
    0.06
    n
    0.06
    lang
    0.06
    Ľ
    0.06
    æĸ¹
    0.06
    gaard
    0.06
     Malone
    0.06
     cof
    0.06
    _COMPILER
    0.06
    anter
    0.06
    Activations Density 0.001%

    No Known Activations