© 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. 5335
    Prev
    Next
    INDEX
    Explanations

    mentions of membership and associated benefits or guidelines

    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
    asu
    -0.07
     Davidson
    -0.06
    eea
    -0.05
    éo
    -0.05
     Wax
    -0.05
    วà¸Ķ
    -0.05
    icensing
    -0.05
    okt
    -0.05
    ee
    -0.05
    ết
    -0.05
    POSITIVE LOGITS
    hip
    0.08
     who
    0.07
    hare
    0.07
    *****/↵
    0.06
    JNIEnv
    0.06
     concession
    0.06
     knull
    0.06
    /not
    0.06
    	ROM
    0.06
    enticate
    0.06
    Activations Density 0.014%

    No Known Activations