© 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. 127396
    Prev
    Next
    INDEX
    Explanations

    the presence of specific, possibly coded terms or identifiers

    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
     Ay
    -0.07
     ay
    -0.06
     Next
    -0.06
    HT
    -0.06
    ging
    -0.06
    te
    -0.06
    ming
    -0.06
     initial
    -0.06
    udge
    -0.06
     inverse
    -0.06
    POSITIVE LOGITS
    usu
    0.08
    iston
    0.08
    estructor
    0.07
    ekil
    0.07
     nues
    0.07
    agal
    0.07
    endor
    0.07
    ends
    0.07
    agt
    0.07
    bsite
    0.07
    Activations Density 0.000%

    No Known Activations