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. 43865
    Prev
    Next
    INDEX
    Explanations

    references to indie music and independent artists

    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
    Indented
    -0.08
    ered
    -0.07
    edly
    -0.07
    edImage
    -0.07
    ings
    -0.07
    INGS
    -0.07
    eners
    -0.07
    ernote
    -0.07
    ↵↵
    -0.06
    idebar
    -0.06
    POSITIVE LOGITS
     dar
    0.11
    -rock
    0.11
     rock
    0.11
     darling
    0.11
    pop
    0.10
    pend
    0.10
    -pop
    0.09
    cred
    0.08
    hone
    0.08
     labels
    0.08
    Activations Density 0.011%

    No Known Activations