© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90206
    Prev
    Next
    INDEX
    Explanations

    references to software project documentation and versioning

    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
    uder
    -0.07
    _pb
    -0.07
     Scratch
    -0.06
    oci
    -0.06
    ÏĦιν
    -0.06
    ifter
    -0.06
    访
    -0.06
     Wayback
    -0.06
    ifa
    -0.06
    ionales
    -0.06
    POSITIVE LOGITS
    engo
    0.07
    itian
    0.06
    ongoose
    0.06
    atron
    0.06
    ữ
    0.06
     unm
    0.06
    hof
    0.06
     support
    0.06
     code
    0.06
    ipar
    0.06
    Activations Density 0.015%

    No Known Activations