© 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. 9-LLAMASCOPE-RES-131K
    11. 94967
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web development frameworks

    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
    zo
    -0.08
    atra
    -0.08
    ÏįÏĦε
    -0.07
     TMPro
    -0.07
    ffen
    -0.07
    asca
    -0.07
    ertas
    -0.07
    .Promise
    -0.07
    libft
    -0.07
    tür
    -0.06
    POSITIVE LOGITS
     Starr
    0.06
     Innoc
    0.06
    dro
    0.06
    memberOf
    0.06
    rawl
    0.06
     Fate
    0.06
    º
    0.05
    trace
    0.05
     fate
    0.05
    寸
    0.05
    Activations Density 0.000%

    No Known Activations