© 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. 106383
    Prev
    Next
    INDEX
    Explanations

    instances of reported speech or dialogue

    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
    avaÅŁ
    -0.08
    ÑĪев
    -0.08
    ahas
    -0.08
    _RM
    -0.08
    abwe
    -0.08
    unik
    -0.07
    ugins
    -0.07
    jvu
    -0.07
    AxisSize
    -0.07
    оÑıн
    -0.07
    POSITIVE LOGITS
     Coy
    0.06
     Sent
    0.06
    ama
    0.06
    ling
    0.05
    razier
    0.05
    ãĤ¹ãĤ¯
    0.05
    sta
    0.05
    ewis
    0.05
     Ed
    0.05
     Sat
    0.05
    Activations Density 0.019%

    No Known Activations