© 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. 81219
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the need for support or provisions for individuals or communities

    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
    ailer
    -0.07
    WillAppear
    -0.07
    EdgeInsets
    -0.07
    ileo
    -0.06
    mh
    -0.06
    CCR
    -0.06
    avian
    -0.06
    zac
    -0.06
    رÙĪس
    -0.06
    c
    -0.06
    POSITIVE LOGITS
    ÃĸL
    0.07
    eyi
    0.07
     ÑģобÑĸ
    0.07
     ourselves
    0.06
     future
    0.06
    .scalablytyped
    0.06
    .lu
    0.06
    amus
    0.06
    297
    0.06
     Hed
    0.06
    Activations Density 0.007%

    No Known Activations