© 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. 27339
    Prev
    Next
    INDEX
    Explanations

    quotes from sports figures and their associated context

    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
    _firestore
    -0.09
    baru
    -0.07
    imde
    -0.07
    hands
    -0.07
    ICI
    -0.07
    oku
    -0.07
    endale
    -0.07
     اÙĦÙĤدÙħ
    -0.07
    ÑıÑģ
    -0.07
    dux
    -0.07
    POSITIVE LOGITS
     coach
    0.07
     Owner
    0.07
     lead
    0.07
     owner
    0.07
    anta
    0.07
    OWNER
    0.06
     co
    0.06
     quarter
    0.06
    Owner
    0.06
     pinch
    0.06
    Activations Density 0.010%

    No Known Activations