© 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. 118770
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Sund" in various contexts

    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
    ister
    -0.08
    ush
    -0.08
    olley
    -0.07
    Ñĩ
    -0.07
    ç
    -0.07
    _ALLOW
    -0.06
    che
    -0.06
    279
    -0.06
    imson
    -0.06
    è¾¼
    -0.06
    POSITIVE LOGITS
    een
    0.07
    -serif
    0.07
    rome
    0.07
    alim
    0.07
    krit
    0.06
    nown
    0.06
    iesel
    0.06
     Stap
    0.06
    ekl
    0.06
    aroo
    0.06
    Activations Density 0.003%

    No Known Activations