© 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. 15-LLAMASCOPE-RES-131K
    11. 86726
    Prev
    Next
    INDEX
    Explanations

    references to accidental mistakes or errors

    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
    FLAG
    -0.07
    ÙĪسÛĮ
    -0.07
     INTERRUPTION
    -0.07
    ailable
    -0.07
    quo
    -0.07
    alc
    -0.07
    idden
    -0.07
    ç·Ĵ
    -0.07
    uche
    -0.06
    ourg
    -0.06
    POSITIVE LOGITS
     instead
    0.12
     Instead
    0.09
    instead
    0.09
    Instead
    0.08
     вмеÑģÑĤ
    0.08
     mistake
    0.07
     yanlÄ±ÅŁ
    0.07
     wrong
    0.07
     meant
    0.07
     substitute
    0.06
    Activations Density 0.026%

    No Known Activations