© 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. 5-LLAMASCOPE-RES-131K
    11. 126781
    Prev
    Next
    INDEX
    Explanations

    references to classic literature or classic works

    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
    алеж
    -0.06
    rawn
    -0.06
    oke
    -0.06
    CoreApplication
    -0.06
    odzi
    -0.06
    ocos
    -0.06
    Ìĥ
    -0.06
    Calibri
    -0.06
    owering
    -0.06
    essen
    -0.06
    POSITIVE LOGITS
    ibel
    0.07
    BOT
    0.07
    rant
    0.07
    æķ·
    0.06
    Hat
    0.06
    εÏĨ
    0.06
    util
    0.06
     Hat
    0.06
     bl
    0.06
     Shortcut
    0.06
    Activations Density 0.004%

    No Known Activations