© 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. 73040
    Prev
    Next
    INDEX
    Explanations

    instances of the word "initial" and related 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
    æł·çļĦ
    -0.08
    zcze
    -0.07
    ess
    -0.07
    alen
    -0.07
    ese
    -0.07
    imas
    -0.07
    alim
    -0.07
    ालत
    -0.07
    ongan
    -0.06
    ats
    -0.06
    POSITIVE LOGITS
    mente
    0.12
    /original
    0.11
    (initial
    0.09
    dehyde
    0.09
    /current
    0.09
    aneously
    0.09
    lest
    0.09
    most
    0.08
    -stage
    0.08
    ities
    0.08
    Activations Density 0.017%

    No Known Activations