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. 31-LLAMASCOPE-RES-131K
    6. 44418
    Prev
    Next
    INDEX
    Explanations

    references to specific years and dates

    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
    idia
    -0.07
    esiz
    -0.06
    tras
    -0.06
    оÑĥ
    -0.06
    Û±Û³
    -0.06
    irtual
    -0.06
     Falk
    -0.06
    sworth
    -0.06
     trio
    -0.06
    stractions
    -0.06
    POSITIVE LOGITS
    700
    0.08
    708
    0.08
    00
    0.08
    7
    0.08
    701
    0.08
    0
    0.07
    014
    0.07
    1
    0.07
    70
    0.07
    600
    0.07
    Activations Density 0.019%

    No Known Activations