© 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. 9-LLAMASCOPE-RES-131K
    11. 94788
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes

    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
    igne
    -0.07
    ueblo
    -0.06
     regress
    -0.06
     Regression
    -0.06
    hetic
    -0.06
    ister
    -0.06
    ttl
    -0.06
    icit
    -0.05
    addtogroup
    -0.05
    ill
    -0.05
    POSITIVE LOGITS
    okit
    0.07
    EFR
    0.07
    _UNUSED
    0.07
    .esp
    0.07
    .tc
    0.07
    .getComponent
    0.07
    .viewDidLoad
    0.07
    _sdk
    0.07
    EMY
    0.07
    ORB
    0.07
    Activations Density 0.008%

    No Known Activations