Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44226
    Prev
    Next
    INDEX
    Explanations

    references to a specific object or instance within a programming context

    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
    sov
    -0.06
    ationToken
    -0.06
     reversible
    -0.06
    ippi
    -0.05
     OECD
    -0.05
     DISCLAIMS
    -0.05
    idd
    -0.05
    esModule
    -0.05
    ades
    -0.05
    ories
    -0.05
    POSITIVE LOGITS
     context
    0.14
     ctxt
    0.12
     mContext
    0.12
     ctx
    0.12
     kont
    0.11
     конÑĤ
    0.11
     applicationContext
    0.11
     cont
    0.11
     cnt
    0.10
     con
    0.10
    Activations Density 0.005%

    No Known Activations