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. 44004
    Prev
    Next
    INDEX
    Explanations

    characters or symbols with high visual complexity

    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
    ’↵
    -0.07
     “
    -0.06
    ’
    -0.06
    nton
    -0.06
     ‘
    -0.06
    ’↵↵
    -0.05
    ‘
    -0.05
    –and
    -0.05
    ogo
    -0.05
    POSITIVE LOGITS
     Dest
    0.11
    Dest
    0.10
     Destiny
    0.09
     Destination
    0.08
    istrovstvÃŃ
    0.08
    DEST
    0.08
     DEST
    0.08
     gradually
    0.08
     -
    0.08
     paranormal
    0.08
    Activations Density 0.002%

    No Known Activations