© 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. 929
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions about significant companies

    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
    urm
    -0.07
    CLE
    -0.07
    YRO
    -0.06
    bah
    -0.06
    acco
    -0.06
     Banc
    -0.06
    lü
    -0.06
    YLON
    -0.06
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.06
    aldo
    -0.06
    POSITIVE LOGITS
    ettle
    0.07
     hedge
    0.06
    åĵ¥
    0.06
     trú
    0.06
    à¤Ĥà¤ļ
    0.06
    æī¶
    0.06
    Äij
    0.06
     earliest
    0.06
    mÃŃ
    0.06
    PEC
    0.06
    Activations Density 0.000%

    No Known Activations