© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61772
    Prev
    Next
    INDEX
    Explanations

    references to digital data management and research resources

    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
     metro
    -0.07
     McCart
    -0.07
     kin
    -0.07
    zos
    -0.06
     phone
    -0.06
    åº
    -0.06
    æģµ
    -0.06
    addy
    -0.06
    Kin
    -0.06
    Alloc
    -0.06
    POSITIVE LOGITS
    rif
    0.07
    'url
    0.07
    earch
    0.07
    æ°¸ä¹ħ
    0.07
    ILON
    0.07
    ilon
    0.07
    Formula
    0.06
     isize
    0.06
    mî
    0.06
    GenerationStrategy
    0.06
    Activations Density 0.003%

    No Known Activations