© 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. 72903
    Prev
    Next
    INDEX
    Explanations

    descriptions of services and offerings, particularly in a business or product 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
    gın
    -0.09
    eder
    -0.06
    uild
    -0.06
    gan
    -0.06
    (norm
    -0.06
    å°Ĥ
    -0.06
     tavs
    -0.06
     desn
    -0.06
     пÑĢоÑĪ
    -0.06
     presses
    -0.05
    POSITIVE LOGITS
    rooms
    0.07
     opportunities
    0.07
    nid
    0.06
    swire
    0.06
    PILE
    0.06
     opportunity
    0.06
    utto
    0.06
    akis
    0.06
    æĺ¥
    0.06
    umer
    0.06
    Activations Density 0.026%

    No Known Activations