© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106110
    Prev
    Next
    INDEX
    Explanations

    instances of the word "during" and related temporal references

    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
    irit
    -0.08
    endor
    -0.07
    gs
    -0.07
    affle
    -0.07
    iki
    -0.07
    cken
    -0.06
    oppel
    -0.06
    ault
    -0.06
    allen
    -0.06
    asl
    -0.06
    POSITIVE LOGITS
     thereof
    0.10
    ãģĿãĤĮãģ¯
    0.10
     Äijó
    0.09
    è¿Ļ个
    0.08
     ấy
    0.08
     ìĿ´ëĬĶ
    0.08
     ìĿ´ë¥¼
    0.08
     dabei
    0.07
    éĤ£éĩĮ
    0.07
     bunu
    0.07
    Activations Density 0.051%

    No Known Activations