© 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. 118774
    Prev
    Next
    INDEX
    Explanations

    phrases indicating permission or authorization

    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
    elah
    -0.07
    izard
    -0.06
    igest
    -0.06
    à¥Įल
    -0.06
    kr
    -0.06
    leftright
    -0.06
    à¸Ļว
    -0.06
    been
    -0.06
    pr
    -0.06
    etrofit
    -0.05
    POSITIVE LOGITS
    ãĤ¿ãĥ«
    0.07
    Ú¯
    0.07
    _GRANTED
    0.07
    ório
    0.07
    icy
    0.07
    atics
    0.06
    yer
    0.06
     Evet
    0.06
    ÏĢε
    0.06
    rea
    0.06
    Activations Density 0.001%

    No Known Activations