© 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. 3669
    Prev
    Next
    INDEX
    Explanations

    references to policies, terms, and conditions related to usage agreements

    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
     Doll
    -0.06
    /graphql
    -0.06
     Bearing
    -0.06
    ëĦIJ
    -0.06
    unden
    -0.06
     comb
    -0.06
     passages
    -0.06
    SError
    -0.05
    arro
    -0.05
    @student
    -0.05
    POSITIVE LOGITS
    ucchini
    0.07
    appings
    0.07
    ets
    0.07
    ilib
    0.07
    riel
    0.07
    urnished
    0.07
     Mile
    0.06
     initState
    0.06
     Sink
    0.06
     Terms
    0.06
    Activations Density 0.002%

    No Known Activations