© 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. 121216
    Prev
    Next
    INDEX
    Explanations

    references to the concept of living or life

    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
    eyh
    -0.07
     smrt
    -0.07
    ounding
    -0.07
    Æł
    -0.07
    lee
    -0.06
    еÑģÑĤо
    -0.06
    евид
    -0.06
    inning
    -0.06
    .scalablytyped
    -0.06
    zyst
    -0.06
    POSITIVE LOGITS
    ogi
    0.06
    astreet
    0.06
    ìĪ
    0.06
    radio
    0.06
    人çī©
    0.06
    olia
    0.06
    .RunWith
    0.06
     inf
    0.06
     senator
    0.06
    rema
    0.05
    Activations Density 0.001%

    No Known Activations