© 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. 97759
    Prev
    Next
    INDEX
    Explanations

    references to technology and product launches

    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
    ukes
    -0.07
    oog
    -0.07
    ufen
    -0.07
    onya
    -0.07
    inker
    -0.06
    bow
    -0.06
    Idle
    -0.06
    onas
    -0.06
     mine
    -0.06
    adoo
    -0.06
    POSITIVE LOGITS
    Argb
    0.08
    ERT
    0.07
    ERE
    0.07
     lifestyles
    0.06
    erville
    0.06
    CoreApplication
    0.06
     Hlav
    0.06
    pha
    0.06
    EOF
    0.06
    StartElement
    0.06
    Activations Density 0.016%

    No Known Activations