© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 988
    Prev
    Next
    INDEX
    Explanations

    references to political discussions and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Usernames or user identifiers in online discussions, forum posts, and Q&A platforms, often appearing in comment sections or citations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    èĿ
    -0.06
    ame
    -0.06
    ä¸ģ
    -0.06
    озÑı
    -0.06
    itchen
    -0.06
    awan
    -0.06
    uta
    -0.06
    istro
    -0.06
    erdale
    -0.06
    .experimental
    -0.06
    POSITIVE LOGITS
     answer
    0.08
     ìĽĥ
    0.07
    æ»
    0.07
     answers
    0.07
    âĻ
    0.07
    Overflow
    0.07
     perv
    0.06
     Wenger
    0.06
     answered
    0.06
     Ñģви
    0.06
    Activations Density 0.004%

    No Known Activations