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. 9-LLAMASCOPE-RES-131K
    6. 96056
    Prev
    Next
    INDEX
    Explanations

    words related to the effectiveness and quality of services or products

    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
    acula
    -0.07
    SEL
    -0.07
    usb
    -0.07
    oine
    -0.07
    ASE
    -0.06
    LL
    -0.06
    anas
    -0.06
     ãģ¾
    -0.06
    kins
    -0.06
    anship
    -0.06
    POSITIVE LOGITS
    ness
    0.07
    utoff
    0.07
    rous
    0.07
    浪
    0.06
    allet
    0.06
    _traits
    0.06
    CHANT
    0.06
    keiten
    0.06
    æķ·
    0.06
    agger
    0.06
    Activations Density 0.036%

    No Known Activations