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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31069
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence or lack of something

    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
    cü
    -0.08
    okit
    -0.08
    oftware
    -0.08
    hiba
    -0.08
    enha
    -0.07
    á»ĩu
    -0.07
    wend
    -0.07
     isize
    -0.07
    ernetes
    -0.07
    ÏĦÏīν
    -0.07
    POSITIVE LOGITS
     worry
    0.09
     consequences
    0.08
     risk
    0.08
     worrying
    0.07
     consequence
    0.07
     fear
    0.07
    af
    0.07
     concern
    0.07
     worried
    0.07
     worries
    0.07
    Activations Density 0.014%

    No Known Activations