© 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. 22-LLAMASCOPE-RES-131K
    11. 4036
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'r' in the text

    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
    unker
    -0.07
    ap
    -0.07
     Rocket
    -0.06
    ÐļÐIJ
    -0.06
    une
    -0.06
    ouched
    -0.06
    uv
    -0.06
    ishops
    -0.06
    HasBeen
    -0.06
    leston
    -0.06
    POSITIVE LOGITS
     r
    0.12
    =r
    0.08
     duplic
    0.07
    orra
    0.07
    жÑĥ
    0.07
     باÙĤ
    0.06
    attle
    0.06
    udder
    0.06
    Ãłn
    0.06
    svp
    0.06
    Activations Density 0.012%

    No Known Activations