© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4211
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate awareness or realization of important information

    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
    emey
    -0.08
    auer
    -0.07
    chein
    -0.07
    endl
    -0.07
    endra
    -0.07
    .pb
    -0.07
    veau
    -0.07
    iyet
    -0.07
    åŀĤ
    -0.07
    ibus
    -0.07
    POSITIVE LOGITS
     realization
    0.09
     realized
    0.09
     knew
    0.09
     realize
    0.08
     indication
    0.08
     realised
    0.07
     began
    0.07
     realizes
    0.07
     hint
    0.07
     begin
    0.07
    Activations Density 0.069%

    No Known Activations