© 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. 22-LLAMASCOPE-RES-131K
    6. 4256
    Prev
    Next
    INDEX
    Explanations

    phrases related to community and collaboration

    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
    ÙĪØ§Ø¡
    -0.08
     bipartisan
    -0.07
    ield
    -0.06
    ixel
    -0.06
    ied
    -0.06
    rael
    -0.06
    cala
    -0.06
    xFFF
    -0.06
    abel
    -0.06
    xFFFFFF
    -0.06
    POSITIVE LOGITS
    etc
    0.07
    ãģĿãģ®ä»ĸ
    0.07
    iyet
    0.07
     etc
    0.07
     miscellaneous
    0.07
    ÐIJÑĢÑħÑĸв
    0.07
    öyle
    0.06
     기íĥĢ
    0.06
     ساÛĮر
    0.06
    _RST
    0.06
    Activations Density 0.023%

    No Known Activations