© 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. 41701
    Prev
    Next
    INDEX
    Explanations

    numerical values and estimates related to costs and projects

    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
    lam
    -0.07
    ÙĪاء
    -0.07
     aggression
    -0.06
    جار
    -0.06
    slash
    -0.06
    WORD
    -0.06
    ãĤ§
    -0.05
    651
    -0.05
     activities
    -0.05
     chrom
    -0.05
    POSITIVE LOGITS
    ussen
    0.07
     Rail
    0.07
    é«ĺéĢŁ
    0.07
    .future
    0.07
    adol
    0.07
     Tunnel
    0.07
     connector
    0.07
    _Speed
    0.07
     speeds
    0.07
    .Pod
    0.07
    Activations Density 0.012%

    No Known Activations