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. 5671
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals or quotations

    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
     "
    -0.07
    arel
    -0.06
    ipheral
    -0.06
    inet
    -0.06
    zier
    -0.06
    anguard
    -0.06
    ìĿµ
    -0.06
    yn
    -0.06
    ando
    -0.06
    :
    -0.05
    POSITIVE LOGITS
     further
    0.08
     Further
    0.07
    -alist
    0.07
     weiter
    0.07
    Further
    0.07
     thêm
    0.07
     **/↵↵
    0.07
     dále
    0.07
    uraa
    0.07
     mastur
    0.06
    Activations Density 0.010%

    No Known Activations