© 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. 54506
    Prev
    Next
    INDEX
    Explanations

    references to methods and projects related to academic or technical work

    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
     Probe
    -0.06
    vik
    -0.06
    ¦
    -0.06
     chairman
    -0.06
     Homework
    -0.06
    ertz
    -0.06
    ardown
    -0.05
    ¤
    -0.05
    boom
    -0.05
     fing
    -0.05
    POSITIVE LOGITS
    alars
    0.09
    ilon
    0.08
    etadata
    0.07
    _Collections
    0.07
     project
    0.07
     JNIEnv
    0.07
    hdl
    0.07
    etler
    0.07
    .site
    0.07
    .twitch
    0.07
    Activations Density 0.000%

    No Known Activations