© 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. 15-LLAMASCOPE-RES-131K
    11. 62248
    Prev
    Next
    INDEX
    Explanations

    fragments of legal or licensing language

    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
    trap
    -0.07
    iger
    -0.07
     Wheel
    -0.07
     Stick
    -0.07
     QuáºŃn
    -0.06
    strom
    -0.06
    stadt
    -0.06
    acs
    -0.06
    Stick
    -0.06
    ilo
    -0.06
    POSITIVE LOGITS
    ãĥ«ãĤ¯
    0.09
     Ridley
    0.07
     mrb
    0.07
    à¥ģà¤Ł
    0.07
    EPHIR
    0.06
    /REC
    0.06
    TRGL
    0.06
    ERRQ
    0.06
     wom
    0.06
    orrar
    0.06
    Activations Density 0.013%

    No Known Activations