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. 5397
    Prev
    Next
    INDEX
    Explanations

    phrases that express negation or exceptions

    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
    fffffff
    -0.07
    utas
    -0.07
    .GetObject
    -0.07
    .Abstractions
    -0.06
     Tanks
    -0.06
    isser
    -0.06
    intr
    -0.06
     Intr
    -0.06
    imit
    -0.06
    outube
    -0.06
    POSITIVE LOGITS
    rog
    0.07
    amment
    0.07
    ippi
    0.06
     exclusively
    0.06
    yte
    0.06
    aign
    0.06
     exclusive
    0.06
    oland
    0.06
     exceptions
    0.06
    rogen
    0.06
    Activations Density 0.008%

    No Known Activations