© 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 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. 16552
    Prev
    Next
    INDEX
    Explanations

    terms related to identifiers in programming or technical documentation

    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
    isman
    -0.09
    ÅĻik
    -0.09
    -fw
    -0.08
    inder
    -0.08
    ilon
    -0.07
    iw
    -0.07
    bery
    -0.07
     Ä°z
    -0.07
    egin
    -0.07
    rise
    -0.07
    POSITIVE LOGITS
    entities
    0.08
    linger
    0.07
    cs
    0.07
     Gentle
    0.07
    ValuePair
    0.06
    ling
    0.06
    и
    0.06
    gent
    0.06
    295
    0.06
     Saul
    0.06
    Activations Density 0.006%

    No Known Activations