© 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. 72121
    Prev
    Next
    INDEX
    Explanations

    references to performance in competitive settings

    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
    iras
    -0.07
    itr
    -0.07
    anel
    -0.06
    amilia
    -0.06
    lucent
    -0.06
    gars
    -0.06
    ienne
    -0.06
    anya
    -0.06
    oker
    -0.06
    avl
    -0.06
    POSITIVE LOGITS
     classroom
    0.09
     courtroom
    0.09
     battlefield
    0.07
     onstage
    0.07
    Unmount
    0.07
     bedroom
    0.07
     workplace
    0.06
     Streets
    0.06
     screen
    0.06
    ãĥ©ãĥĥãĤ¯
    0.06
    Activations Density 0.105%

    No Known Activations