© 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. 124999
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses 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
    lings
    -0.08
    Interop
    -0.08
    akis
    -0.07
    ttp
    -0.07
    rpc
    -0.07
     Rudd
    -0.06
    ɵ
    -0.06
    tk
    -0.06
    psilon
    -0.06
    NibName
    -0.06
    POSITIVE LOGITS
    pez
    0.07
     paralle
    0.07
    /REC
    0.06
    zsche
    0.06
    aspers
    0.06
    ëĵł
    0.06
    .closed
    0.06
     ÙĤÙĬ
    0.06
     Sev
    0.06
    /if
    0.06
    Activations Density 0.001%

    No Known Activations