© 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. 15-LLAMASCOPE-RES-131K
    11. 86650
    Prev
    Next
    INDEX
    Explanations

    sentences that indicate the importance or prevalence of a subject

    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
    igar
    -0.07
    ÏįÏĦε
    -0.07
    arch
    -0.06
    ứ
    -0.06
    ction
    -0.06
     First
    -0.06
    αιν
    -0.06
    νÏĦ
    -0.06
    ủ
    -0.06
    ignKey
    -0.06
    POSITIVE LOGITS
    Unfortunately
    0.09
     Unfortunately
    0.09
     unfortunately
    0.08
    Sadly
    0.07
     maar
    0.07
    BOSE
    0.07
     pero
    0.07
    ubat
    0.07
    sko
    0.07
    UBLE
    0.07
    Activations Density 0.020%

    No Known Activations