© 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. 17-LLAMASCOPE-RES-131K
    11. 118069
    Prev
    Next
    INDEX
    Explanations

    programming language elements related to data types and their 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
    oret
    -0.07
    endo
    -0.06
     retract
    -0.06
    lav
    -0.06
     Chelsea
    -0.06
    uno
    -0.06
    arios
    -0.06
     cones
    -0.06
    ijd
    -0.06
    dain
    -0.06
    POSITIVE LOGITS
    zers
    0.07
    çļĦæĺ¯
    0.07
    å°¼äºļ
    0.07
     strokeLine
    0.07
    asurer
    0.07
    bette
    0.07
    ãĥ³ãĥ
    0.06
    ReadStream
    0.06
     ÐĴики
    0.06
    gnore
    0.06
    Activations Density 0.019%

    No Known Activations