© 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 EvalsExportsinterp-engineNEWAPI 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. 54243
    Prev
    Next
    INDEX
    Explanations

    references to customization and adjustments in various 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
    onom
    -0.07
    879
    -0.06
    509
    -0.06
    oni
    -0.06
    organization
    -0.06
    å£
    -0.06
    ä¸Ī
    -0.06
     plate
    -0.06
    AGO
    -0.06
    zp
    -0.06
    POSITIVE LOGITS
     topic
    0.14
    topic
    0.12
     subject
    0.11
    .topic
    0.11
     Topic
    0.10
    Topic
    0.10
    -topic
    0.09
    /topic
    0.09
    ALSE
    0.08
     issue
    0.08
    Activations Density 0.053%

    No Known Activations