© 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. 4014
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and functions

    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
    obic
    -0.07
    chner
    -0.07
    edly
    -0.07
    oda
    -0.07
    avanaugh
    -0.06
     Miles
    -0.06
    subtype
    -0.06
    IVAL
    -0.06
    ibal
    -0.06
    velopment
    -0.06
    POSITIVE LOGITS
    ization
    0.07
     veter
    0.07
    -ÑĤо
    0.06
    izing
    0.06
    ised
    0.06
    _VM
    0.06
     busy
    0.06
    n
    0.06
    ized
    0.06
    urdy
    0.06
    Activations Density 0.000%

    No Known Activations