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. 44359
    Prev
    Next
    INDEX
    Explanations

    negative contractions or forms of denial

    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
     “
    -0.07
     ‘
    -0.07
     www
    -0.06
     ”
    -0.06
    throat
    -0.06
    ,’’
    -0.06
    uluk
    -0.06
     Webster
    -0.05
     “â̦
    -0.05
    stown
    -0.05
    POSITIVE LOGITS
    ws
    0.08
    w
    0.07
     manually
    0.07
    ot
    0.07
     succesfully
    0.06
    _work
    0.06
    amespace
    0.06
    wnd
    0.06
    ->_
    0.06
     âĩĴ
    0.06
    Activations Density 0.034%

    No Known Activations