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. 95848
    Prev
    Next
    INDEX
    Explanations

    references to animal behavior and movement

    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
    quee
    -0.07
    åµ
    -0.07
    Ưá»
    -0.07
    IVES
    -0.07
     æĴ
    -0.07
    иÑĨин
    -0.07
    625
    -0.07
    à¹Īวย
    -0.07
    .FLOAT
    -0.06
    оÑĤов
    -0.06
    POSITIVE LOGITS
    loquent
    0.07
     pre
    0.06
    atial
    0.06
     corn
    0.06
     Judge
    0.06
     Concepts
    0.05
     until
    0.05
     sweet
    0.05
     ev
    0.05
     Natur
    0.05
    Activations Density 0.000%

    No Known Activations