© 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. 69684
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with specific identifiers or data points

    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
    ILD
    -0.07
    uš
    -0.07
    ldb
    -0.07
    628
    -0.07
    ãĢħ
    -0.07
    iag
    -0.07
    بر
    -0.06
    rosse
    -0.06
    ümü
    -0.06
    ROLLER
    -0.06
    POSITIVE LOGITS
     sayılı
    0.08
     Ness
    0.06
    akis
    0.06
    oner
    0.06
    Ñģклад
    0.06
    ev
    0.06
     Castillo
    0.06
    pend
    0.06
     Cabinet
    0.06
    atically
    0.06
    Activations Density 0.077%

    No Known Activations