© 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 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. 17-LLAMASCOPE-RES-131K
    11. 88437
    Prev
    Next
    INDEX
    Explanations

    specific encoded or formatted strings likely representing languages or technical data

    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
    ides
    -0.07
    chema
    -0.07
    illed
    -0.07
    ids
    -0.07
    oteca
    -0.06
    ÎķΣ
    -0.06
    еÑģÑĮ
    -0.06
    eum
    -0.06
    ewidth
    -0.06
    esz
    -0.06
    POSITIVE LOGITS
    temps
    0.07
    ruh
    0.07
     Dynamics
    0.06
    SSIP
    0.06
    ober
    0.06
     dynamics
    0.06
    cats
    0.06
    ween
    0.06
     affairs
    0.06
    lie
    0.06
    Activations Density 0.000%

    No Known Activations