© 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. 71175
    Prev
    Next
    INDEX
    Explanations

    structured data types and definitions, particularly in programming or coding contexts

    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
    land
    -0.06
    ier
    -0.06
    rint
    -0.06
     novelty
    -0.06
    -St
    -0.06
     hu
    -0.06
    yr
    -0.06
     proper
    -0.06
     moments
    -0.06
    Sampler
    -0.06
    POSITIVE LOGITS
    ζί
    0.07
    ulk
    0.07
    chied
    0.07
    ordova
    0.07
    compat
    0.07
    iyon
    0.07
    imizer
    0.07
    OKIE
    0.07
    ChangedEventArgs
    0.07
    unj
    0.06
    Activations Density 0.021%

    No Known Activations