© 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. 29137
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific research conclusions and publications

    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
    overy
    -0.07
    anzi
    -0.07
     addCriterion
    -0.06
    yi
    -0.06
    OCI
    -0.06
    andaÅŁ
    -0.06
    uploaded
    -0.06
    iture
    -0.06
    Łèĥ½
    -0.06
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.06
    POSITIVE LOGITS
    bish
    0.08
    ãĥĥãĥĦ
    0.07
    atcher
    0.06
    AccessException
    0.06
    Reusable
    0.06
    dera
    0.06
    Scar
    0.06
    iglia
    0.06
    inkel
    0.06
    oky
    0.06
    Activations Density 0.048%

    No Known Activations