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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77168
    Prev
    Next
    INDEX
    Explanations

    instances of repetitive phrases or expressions, particularly those involving actions and social interactions

    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
    abox
    -0.07
    airy
    -0.07
    umas
    -0.07
    ç¸
    -0.07
    iani
    -0.07
     عÙħÙĦÛĮ
    -0.07
    thur
    -0.07
    trap
    -0.07
    ObjectContext
    -0.07
    _atomic
    -0.06
    POSITIVE LOGITS
     occasionally
    0.07
     subs
    0.07
     eventual
    0.07
     vie
    0.06
    occ
    0.06
     talk
    0.06
     ev
    0.06
     enjoy
    0.06
     pass
    0.06
     hoping
    0.06
    Activations Density 0.039%

    No Known Activations