Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5329
    Prev
    Next
    INDEX
    Explanations

    phrases related to the creation and development of lasting quality or value

    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
     вÑĩ
    -0.07
    _userdata
    -0.07
    eprom
    -0.07
    à¤Ĥश
    -0.07
    udeau
    -0.07
    PFN
    -0.07
    าà¸ĩ
    -0.07
    ););↵
    -0.07
    ocy
    -0.07
    duc
    -0.07
    POSITIVE LOGITS
     reputation
    0.11
     reput
    0.11
     Reputation
    0.09
     close
    0.08
     expertise
    0.08
     itself
    0.07
     relationships
    0.07
     friendships
    0.07
     himself
    0.07
     throughout
    0.06
    Activations Density 0.015%

    No Known Activations