© 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. 85387
    Prev
    Next
    INDEX
    Explanations

    units of measurement related to substances, particularly in scientific contexts

    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
    egend
    -0.07
    .metamodel
    -0.07
    oss
    -0.06
    bane
    -0.06
    olet
    -0.06
    -toggler
    -0.06
     Spears
    -0.06
    evil
    -0.06
    lay
    -0.06
    fullscreen
    -0.06
    POSITIVE LOGITS
    inal
    0.07
    -per
    0.07
    ìĶ©
    0.06
     per
    0.06
    ulla
    0.06
    reinterpret
    0.06
    âĶĢâĶĢâĶĢâĶĢ
    0.06
    å·¦åı³
    0.06
    ola
    0.06
    kf
    0.06
    Activations Density 0.016%

    No Known Activations