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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 95546
    Prev
    Next
    INDEX
    Explanations

    data and statistics related to market research and industry reports

    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
     (
    -0.06
    S
    -0.06
     
    -0.06
    uby
    -0.06
    ilt
    -0.05
     Catalog
    -0.05
     mal
    -0.05
     St
    -0.05
    out
    -0.05
     bio
    -0.05
    POSITIVE LOGITS
    .synthetic
    0.08
    ompiler
    0.08
    krom
    0.08
     jadx
    0.08
     Kürt
    0.08
    stants
    0.08
    άÏĥ
    0.08
    -LAST
    0.08
    OMIC
    0.07
    ibir
    0.07
    Activations Density 0.023%

    No Known Activations