© 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. 95560
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaborative efforts and community support

    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
    asca
    -0.07
    Contain
    -0.06
     olm
    -0.06
    engl
    -0.06
     anomaly
    -0.06
     Fowler
    -0.06
    èĥ
    -0.06
     issue
    -0.06
    tere
    -0.06
    ancel
    -0.06
    POSITIVE LOGITS
     ways
    0.09
     Ways
    0.08
    thumb
    0.07
    Try
    0.07
    ادÙħ
    0.06
    roker
    0.06
    ettings
    0.06
     Try
    0.06
    ietf
    0.06
    ÙĦÙĦ
    0.06
    Activations Density 0.021%

    No Known Activations