© 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. 118776
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that contain periods, indicating the end of thoughts or sentences

    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
    amet
    -0.08
    .same
    -0.08
    utow
    -0.07
    seealso
    -0.07
    ëłµ
    -0.07
    éĢģæĸĻçĦ¡æĸĻ
    -0.07
    yonel
    -0.07
     Sesso
    -0.07
    iç
    -0.07
     Bölüm
    -0.06
    POSITIVE LOGITS
     respectively
    0.13
     first
    0.09
     respective
    0.08
    åĪĨåĪ«
    0.08
    respect
    0.08
     Firstly
    0.08
     former
    0.07
     First
    0.07
    First
    0.07
     ÑģооÑĤвеÑĤ
    0.07
    Activations Density 0.067%

    No Known Activations