© 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. 92836
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" and its variations

    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
     fitte
    -0.06
    gne
    -0.06
    arna
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
     again
    -0.06
    -0.06
     begin
    -0.06
    ãĥĸãĥ«
    -0.06
    нка
    -0.06
     koneÄį
    -0.06
    POSITIVE LOGITS
    ä¸ĭåİ»
    0.10
    azen
    0.07
     until
    0.07
    OOM
    0.07
    .BackgroundColor
    0.07
     Until
    0.07
    оÑĤÑĭ
    0.07
     mesel
    0.07
    until
    0.07
    uter
    0.06
    Activations Density 0.011%

    No Known Activations