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

    Neuronpedia

    APICircuit 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. 5450
    Prev
    Next
    INDEX
    Explanations

    references to qualities, characteristics, and comparisons related to students, acts, and organizational attributes

    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
    तर
    -0.07
    ESCO
    -0.06
    ugin
    -0.06
    izar
    -0.06
    .sourceforge
    -0.06
    insky
    -0.06
    VD
    -0.06
    assy
    -0.06
    Defaults
    -0.06
    occo
    -0.06
    POSITIVE LOGITS
     successful
    0.20
     good
    0.19
    successful
    0.16
    good
    0.15
     Successful
    0.15
     truly
    0.15
     effective
    0.14
     ÑħоÑĢоÑĪ
    0.14
    Successful
    0.14
    好çļĦ
    0.13
    Activations Density 0.043%

    No Known Activations