© 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. 94824
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that express possibilities or obligations

    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
     was
    -0.09
    imon
    -0.07
     wasn
    -0.07
    was
    -0.07
    gren
    -0.07
     бÑĭло
    -0.06
    ¸ı
    -0.06
     бÑĥло
    -0.06
     бÑĭла
    -0.06
    ston
    -0.06
    POSITIVE LOGITS
    ĥģ
    0.07
    nodoc
    0.07
    zik
    0.07
     Barg
    0.07
    urnal
    0.07
    ontent
    0.07
    _HAL
    0.07
     Rip
    0.06
    lessly
    0.06
    igs
    0.06
    Activations Density 0.066%

    No Known Activations