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. 44109
    Prev
    Next
    INDEX
    Explanations

    titles of books and significant literary themes

    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
    ,eg
    -0.10
    ÑĪиб
    -0.09
    (æ°´
    -0.09
    (æľ¨
    -0.09
     dư
    -0.09
    .COL
    -0.08
    (çģ«
    -0.08
     POLL
    -0.08
     ALERT
    -0.08
    quential
    -0.08
    POSITIVE LOGITS
     the
    0.10
    Âł
    0.09
     a
    0.09
     Âł
    0.08
     of
    0.08
     Tb
    0.08
     and
    0.08
     Particularly
    0.08
    <|end_of_text|>
    0.08
    _
    0.08
    Activations Density 0.038%

    No Known Activations