Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5326
    Prev
    Next
    INDEX
    Explanations

    negations or denials

    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
    erin
    -0.07
    usterity
    -0.07
    ipped
    -0.06
    erp
    -0.06
     Fluent
    -0.06
    adro
    -0.06
    loth
    -0.06
    flare
    -0.06
    oppable
    -0.06
    ãĤ¢ãĥ³
    -0.06
    POSITIVE LOGITS
    IRST
    0.07
    kud
    0.07
    _lhs
    0.07
    mnt
    0.06
    ordion
    0.06
    (Window
    0.06
     zá
    0.06
     Brow
    0.06
     Coral
    0.06
    _requirements
    0.06
    Activations Density 0.000%

    No Known Activations