© 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. 40103
    Prev
    Next
    INDEX
    Explanations

    mentions of time, events, or notable occurrences

    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
    -exc
    -0.07
     queryInterface
    -0.07
    oir
    -0.07
    omite
    -0.07
    ultipartFile
    -0.06
     jt
    -0.06
    ño
    -0.06
     initWithStyle
    -0.06
    rove
    -0.06
    orio
    -0.06
    POSITIVE LOGITS
    atos
    0.07
    _decorator
    0.06
    caret
    0.06
    203
    0.06
    æķ
    0.06
     bos
    0.06
     Reuters
    0.06
     í
    0.06
     Bos
    0.06
     Labs
    0.06
    Activations Density 0.004%

    No Known Activations