© 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. 14854
    Prev
    Next
    INDEX
    Explanations

    notes or comments of clarification in the text

    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
    ogan
    -0.07
     Hooks
    -0.06
    .osgi
    -0.06
    akis
    -0.06
    182
    -0.06
     eventual
    -0.06
    ondo
    -0.06
    anas
    -0.05
    555
    -0.05
    earer
    -0.05
    POSITIVE LOGITS
     regarding
    0.08
    £¼
    0.07
    ÑĢежд
    0.07
    :&
    0.07
    azers
    0.07
    LBL
    0.07
    viso
    0.07
    ा:
    0.07
    ioned
    0.07
    note
    0.07
    Activations Density 0.010%

    No Known Activations