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. 22-LLAMASCOPE-RES-131K
    6. 5733
    Prev
    Next
    INDEX
    Explanations

    references to albums, including their titles and details about their release and track listings

    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
    ssf
    -0.07
    alink
    -0.07
    anter
    -0.07
    antino
    -0.07
    anken
    -0.06
    sov
    -0.06
    λεί
    -0.06
    ber
    -0.06
    osten
    -0.06
    WithOptions
    -0.06
    POSITIVE LOGITS
     released
    0.08
     release
    0.08
    _RELEASE
    0.08
    release
    0.07
    released
    0.07
     releasing
    0.07
    Released
    0.07
    .DropTable
    0.07
     releases
    0.07
     вÑĭп
    0.07
    Activations Density 0.007%

    No Known Activations