© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84480
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Quint" and related variations

    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
    otland
    -0.07
    odable
    -0.07
     SPF
    -0.07
    ationToken
    -0.07
    ulet
    -0.07
    hesive
    -0.07
    lems
    -0.06
    ised
    -0.06
    Ø«ÛĮر
    -0.06
    edException
    -0.06
    POSITIVE LOGITS
    uple
    0.09
    agram
    0.08
    atic
    0.08
    essential
    0.07
    etter
    0.07
    opia
    0.07
     vou
    0.07
    ana
    0.07
    ByExample
    0.07
     chance
    0.06
    Activations Density 0.004%

    No Known Activations