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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40970
    Prev
    Next
    INDEX
    Explanations

    references to copyright

    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
     revers
    -0.07
     Desire
    -0.07
    ohan
    -0.06
     Gabri
    -0.06
    -
    -0.06
     Hib
    -0.06
    ensburg
    -0.06
     tie
    -0.05
     recom
    -0.05
    _registry
    -0.05
    POSITIVE LOGITS
    astreet
    0.07
    lero
    0.07
     rall
    0.07
     zby
    0.07
    imen
    0.07
     eviction
    0.07
    (fil
    0.06
     åı·
    0.06
     ruk
    0.06
    åľ¨çº¿è§Ĩé¢ij
    0.06
    Activations Density 0.000%

    No Known Activations