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. 43627
    Prev
    Next
    INDEX
    Explanations

    references to the Bering Sea and its associated fisheries

    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
    :param
    -0.07
     Kahn
    -0.06
    åĢĴ
    -0.06
     Gilbert
    -0.06
    Undo
    -0.06
    edis
    -0.06
    spect
    -0.06
    imator
    -0.06
    utory
    -0.06
    drv
    -0.06
    POSITIVE LOGITS
    ight
    0.14
    ays
    0.14
    arent
    0.13
    ering
    0.12
    ights
    0.11
    alt
    0.10
    ay
    0.10
    osph
    0.10
    ayah
    0.10
    ucht
    0.10
    Activations Density 0.011%

    No Known Activations