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. 9-LLAMASCOPE-RES-131K
    6. 96073
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of doubt and uncertainty

    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
    sizeof
    -0.06
    park
    -0.06
    oi
    -0.06
    arih
    -0.06
    dis
    -0.05
    dt
    -0.05
    appa
    -0.05
     Dah
    -0.05
     Exc
    -0.05
    ceptive
    -0.05
    POSITIVE LOGITS
    quam
    0.08
    çļĦè¯Ŀ
    0.07
    RTL
    0.07
    #ab
    0.07
    imet
    0.07
    елик
    0.07
    istrovstvÃŃ
    0.07
    eyse
    0.07
    å°ļ
    0.07
    .win
    0.07
    Activations Density 0.023%

    No Known Activations