© 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. 92306
    Prev
    Next
    INDEX
    Explanations

    phrases that establish relationships or conditions in legal statements

    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
    ÏĦÏī
    -0.07
    mere
    -0.07
    ÙĪÛĮÙĩ
    -0.07
     ÎłÎ¿
    -0.07
    742
    -0.07
     reperc
    -0.07
    istine
    -0.06
     СÑĤаÑĢ
    -0.06
    ioni
    -0.06
    Ñħодим
    -0.06
    POSITIVE LOGITS
     neither
    0.07
    :↵
    0.06
     observed
    0.06
     although
    0.06
    observable
    0.06
     certain
    0.06
    ammable
    0.06
    selectors
    0.05
    ensor
    0.05
     while
    0.05
    Activations Density 0.030%

    No Known Activations