© 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 EvalsExportsAPI 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. 85546
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proximity and convenience

    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
     åī
    -0.08
    afil
    -0.07
    åī
    -0.07
    jeme
    -0.07
    omics
    -0.06
    ascimento
    -0.06
    usty
    -0.06
    agini
    -0.06
    anity
    -0.06
    YW
    -0.06
    POSITIVE LOGITS
     mere
    0.07
     hop
    0.07
    ünd
    0.07
    771
    0.06
    mere
    0.06
    )const
    0.06
    bart
    0.06
    ìķħ
    0.06
     Hopkins
    0.06
     babys
    0.06
    Activations Density 0.010%

    No Known Activations