© 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. 106851
    Prev
    Next
    INDEX
    Explanations

    content related to career information

    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
    аÑĢам
    -0.06
    onga
    -0.06
    busters
    -0.06
     Daw
    -0.06
    348
    -0.06
    hee
    -0.06
    å¢ŀ
    -0.06
    æij¸
    -0.06
    lash
    -0.06
     Trem
    -0.06
    POSITIVE LOGITS
    ãĥ´ãĤ¡
    0.07
    achinery
    0.07
     rnd
    0.06
    ãĥģãĥ¥
    0.06
    eu
    0.06
     ฿
    0.06
     Tuple
    0.06
    ais
    0.06
    gaard
    0.06
    _codegen
    0.06
    Activations Density 0.000%

    No Known Activations