© 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. 61338
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to document formatting and structure

    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
    leck
    -0.07
    essen
    -0.06
    iture
    -0.06
    unami
    -0.06
    upy
    -0.06
    unks
    -0.06
    ิà¸Ĺยา
    -0.06
    hots
    -0.06
    ught
    -0.06
     LRV
    -0.06
    POSITIVE LOGITS
    çĵľ
    0.08
    errer
    0.08
    pt
    0.07
    åŁŁ
    0.06
    ifestyles
    0.06
    ìĿ´ìĬ¤
    0.06
    yd
    0.06
     Bilim
    0.06
    uitka
    0.06
     Dann
    0.06
    Activations Density 0.047%

    No Known Activations