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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119234
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases that seek clarification or inquiry into various subjects

    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
    åĤ
    -0.06
    aland
    -0.06
    âĢª
    -0.06
     Pioneer
    -0.06
    869
    -0.06
     Trad
    -0.06
    assa
    -0.06
    ãĥ©ãĤ¤ãĥ³
    -0.06
     Hos
    -0.06
     tôn
    -0.06
    POSITIVE LOGITS
    odzi
    0.07
    ahi
    0.07
    mgr
    0.07
    ÑĤÑİ
    0.07
    chyb
    0.07
     irresist
    0.06
    etros
    0.06
    ingleton
    0.06
    /stdc
    0.06
    /Runtime
    0.06
    Activations Density 0.062%

    No Known Activations