© 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. 98603
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    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
    HL
    -0.06
    odon
    -0.06
    yst
    -0.06
    odont
    -0.06
    iche
    -0.06
    annah
    -0.06
    tement
    -0.05
    hl
    -0.05
    ance
    -0.05
    ifest
    -0.05
    POSITIVE LOGITS
    idis
    0.08
    «ĺ
    0.07
    .netflix
    0.07
    .IContainer
    0.07
     dün
    0.07
    禮
    0.06
    å§ĵ
    0.06
    idge
    0.06
    wyn
    0.06
    кÑĥÑģ
    0.06
    Activations Density 0.000%

    No Known Activations