© 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. 15-LLAMASCOPE-RES-131K
    11. 61384
    Prev
    Next
    INDEX
    Explanations

    references to variables in a programming context

    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
     commissions
    -0.07
    asz
    -0.07
    ernal
    -0.07
    ngrx
    -0.07
    thouse
    -0.07
    reira
    -0.07
    monic
    -0.07
    ninger
    -0.07
    ule
    -0.07
    opoly
    -0.06
    POSITIVE LOGITS
    ç°
    0.07
    egis
    0.06
    afc
    0.06
    odo
    0.06
     Sal
    0.06
    åĢŁ
    0.05
    IVO
    0.05
     Bü
    0.05
     bo
    0.05
    orts
    0.05
    Activations Density 0.001%

    No Known Activations