© 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. 54439
    Prev
    Next
    INDEX
    Explanations

    phrases related to biological and environmental interactions

    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
    urch
    -0.06
    opp
    -0.06
    isay
    -0.06
     Highlights
    -0.06
    ocoa
    -0.06
    erte
    -0.06
    ugu
    -0.06
     small
    -0.05
     cul
    -0.05
    opo
    -0.05
    POSITIVE LOGITS
    target
    0.08
     targetType
    0.08
    ateria
    0.08
    à§į
    0.08
    OCUS
    0.08
     addTarget
    0.07
     оÑħ
    0.07
    ework
    0.07
    ToWorld
    0.07
    ìłĿ
    0.07
    Activations Density 0.040%

    No Known Activations