© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29906
    Prev
    Next
    INDEX
    Explanations

    programming constructs and operations related to data structures

    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
    actal
    -0.07
    afia
    -0.07
    ÄIJT
    -0.07
    AttributeName
    -0.07
     lands
    -0.07
    @student
    -0.07
    å®ħ
    -0.07
    eden
    -0.07
    lech
    -0.07
     ÙģÙĩرست
    -0.07
    POSITIVE LOGITS
     X
    0.06
     essence
    0.06
     
    0.06
    ellar
    0.06
    uchos
    0.06
     (
    0.06
    729
    0.05
     lou
    0.05
    ÑĥлÑİ
    0.05
    481
    0.05
    Activations Density 0.050%

    No Known Activations