© 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. 105404
    Prev
    Next
    INDEX
    Explanations

    financial figures and estimates within the text

    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
    리카
    -0.08
    entifier
    -0.08
    족
    -0.08
     Ñģигн
    -0.07
    ÙĬÙĥÙĬ
    -0.07
    .Accessible
    -0.07
    ÑĢеж
    -0.07
    Æ°á»Ľ
    -0.07
    QRST
    -0.07
     ÑģобÑĭ
    -0.07
    POSITIVE LOGITS
     [[]
    0.07
     none
    0.06
    -none
    0.05
    ContentView
    0.05
    ahoma
    0.05
    addin
    0.05
     .↵
    0.05
    pekt
    0.05
    ?s
    0.05
     Neon
    0.05
    Activations Density 0.024%

    No Known Activations