© 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 EvalsExportsinterp-engineNEWAPI 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. 105110
    Prev
    Next
    INDEX
    Explanations

    mentions of social media handles or usernames

    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
    arer
    -0.06
    asan
    -0.06
    idine
    -0.06
    unya
    -0.06
     pl
    -0.06
    reira
    -0.06
    ẩu
    -0.06
    bes
    -0.06
    anded
    -0.06
    lu
    -0.06
    POSITIVE LOGITS
    CommandLine
    0.08
    leÅŁme
    0.07
    Falsy
    0.07
    CommandEvent
    0.07
    viso
    0.07
     Hlav
    0.07
     åī
    0.06
    getc
    0.06
    ืà¹ī
    0.06
    ovnÃŃ
    0.06
    Activations Density 0.004%

    No Known Activations