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

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126817
    Prev
    Next
    INDEX
    Explanations

    code snippets related to database table operations

    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
     Ud
    -0.07
    icz
    -0.07
    adapter
    -0.06
    /stdc
    -0.06
    readcr
    -0.06
    anik
    -0.06
    .jd
    -0.06
    úi
    -0.06
    lingen
    -0.06
    minating
    -0.06
    POSITIVE LOGITS
     Daniels
    0.06
    å±ĭ
    0.06
    ilia
    0.06
    Bay
    0.06
    asy
    0.06
    EFF
    0.06
     core
    0.06
    avia
    0.06
     Eff
    0.06
    /from
    0.05
    Activations Density 0.000%

    No Known Activations