© 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. 85295
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "that."

    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
    ÑĤож
    -0.09
     Erf
    -0.07
     chances
    -0.07
    á»ī
    -0.07
    orest
    -0.07
    Äįem
    -0.07
    ledi
    -0.07
    овÑĸд
    -0.07
     ç¯
    -0.07
    ãĤŃãĥ³ãĤ°
    -0.07
    POSITIVE LOGITS
     be
    0.08
     should
    0.07
     you
    0.07
     Should
    0.07
     haya
    0.07
     somehow
    0.07
    should
    0.06
    941
    0.06
    hta
    0.06
    Should
    0.06
    Activations Density 0.016%

    No Known Activations