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. 5318
    Prev
    Next
    INDEX
    Explanations

    references to specific players, particularly those with the name "Will" or variations of "Bill."

    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
    beros
    -0.06
    اش
    -0.06
     Willow
    -0.06
    drs
    -0.06
    çĭĹ
    -0.06
    ulla
    -0.06
    ást
    -0.06
    oog
    -0.06
    gable
    -0.06
    .Modules
    -0.05
    POSITIVE LOGITS
    udas
    0.07
    fried
    0.07
    ams
    0.07
    uve
    0.07
     Sesso
    0.07
    гал
    0.06
    iez
    0.06
    inson
    0.06
     mus
    0.06
     Mus
    0.06
    Activations Density 0.006%

    No Known Activations