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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93435
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and code syntax elements

    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
     Euro
    -0.07
    Euro
    -0.06
     liability
    -0.06
    adden
    -0.06
     manifestation
    -0.06
    -sub
    -0.05
    nt
    -0.05
     Ihnen
    -0.05
     McCarthy
    -0.05
     Freak
    -0.05
    POSITIVE LOGITS
    ofile
    0.07
    ERY
    0.07
    é±
    0.07
    WithPath
    0.07
    edImage
    0.07
    sWith
    0.07
    uo
    0.07
    EqualityComparer
    0.07
    umped
    0.07
    renal
    0.07
    Activations Density 0.004%

    No Known Activations