© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82548
    Prev
    Next
    INDEX
    Explanations

    references to databases and profiles related to services

    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
    blr
    -0.07
    ảnh
    -0.07
    challenge
    -0.07
    æ£ļ
    -0.07
     culture
    -0.07
    burger
    -0.06
    kas
    -0.06
    culture
    -0.06
     Culture
    -0.06
     Staples
    -0.06
    POSITIVE LOGITS
     directory
    0.12
    directory
    0.10
     Directory
    0.10
     directories
    0.10
     DIRECTORY
    0.09
     listings
    0.09
    -directory
    0.09
     listing
    0.09
    Directory
    0.09
    _DIRECTORY
    0.08
    Activations Density 0.030%

    No Known Activations