© 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. 17-LLAMASCOPE-RES-131K
    6. 61360
    Prev
    Next
    INDEX
    Explanations

    mentions of public statements and acknowledgments in the context of scandals

    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
    asti
    -0.07
    zano
    -0.07
    меÑĩ
    -0.07
    ased
    -0.06
    argin
    -0.06
    uyo
    -0.06
    adol
    -0.06
     dies
    -0.06
     Dies
    -0.06
    eways
    -0.06
    POSITIVE LOGITS
     spoke
    0.08
     finally
    0.07
     speak
    0.07
     speaking
    0.07
     silence
    0.07
     address
    0.07
    irmware
    0.06
     respond
    0.06
     addressing
    0.06
     Speak
    0.06
    Activations Density 0.021%

    No Known Activations