© 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. 58861
    Prev
    Next
    INDEX
    Explanations

    specific measurements and numerical values related to quantities or statistics

    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
    fter
    -0.07
    ocol
    -0.06
    rtype
    -0.06
    豪
    -0.06
    ancias
    -0.06
     contr
    -0.06
    ancia
    -0.06
    ازÙĦ
    -0.06
    ernal
    -0.06
    ãĤ¤ãĥ«
    -0.06
    POSITIVE LOGITS
     slightly
    0.14
    ycz
    0.08
     slight
    0.08
     precise
    0.07
    erer
    0.07
     exact
    0.07
    affer
    0.07
    .strict
    0.07
     tiny
    0.07
    ç¨į
    0.07
    Activations Density 0.105%

    No Known Activations