© 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. 86963
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or findings

    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
     Weeks
    -0.06
     interrupt
    -0.06
    reff
    -0.05
     Orig
    -0.05
     act
    -0.05
     international
    -0.05
    ctions
    -0.05
     initial
    -0.05
     conven
    -0.05
    izoph
    -0.05
    POSITIVE LOGITS
    egl
    0.09
    anela
    0.08
     Bucc
    0.07
    /Internal
    0.07
    ãĥ©ãĥ¼
    0.07
    ikel
    0.07
    æ¶Ī
    0.07
    roj
    0.07
    ÐĨн
    0.07
     Responsive
    0.07
    Activations Density 0.001%

    No Known Activations