© 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. 61996
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'E' and its variations

    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
    å·¡
    -0.07
    REFIX
    -0.06
    çĶ°
    -0.06
    vu
    -0.06
    Ïģε
    -0.06
     siden
    -0.06
    aled
    -0.06
    mas
    -0.06
     haystack
    -0.06
    REATED
    -0.06
    POSITIVE LOGITS
    onne
    0.07
    plorer
    0.07
    lette
    0.07
    eyin
    0.06
    ofday
    0.06
    asics
    0.06
    ei
    0.06
    enton
    0.06
    iÄįky
    0.06
    .insertBefore
    0.06
    Activations Density 0.007%

    No Known Activations