© 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. 5443
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or repetition

    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
    ourt
    -0.08
    veau
    -0.07
    urd
    -0.07
    ils
    -0.06
    ú
    -0.06
    angan
    -0.06
    å½
    -0.06
    SelectionMode
    -0.06
    ptal
    -0.06
    Forge
    -0.06
    POSITIVE LOGITS
    ryn
    0.07
    abbr
    0.07
     frequent
    0.07
    ë§Īëĭ¤
    0.07
    анÑĮ
    0.06
    getter
    0.06
    EVENT
    0.06
    祥
    0.06
    次æķ°
    0.06
     次
    0.06
    Activations Density 0.007%

    No Known Activations