© 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 EvalsExportsAPI 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. 29271
    Prev
    Next
    INDEX
    Explanations

    identifiers related to coding structure or function

    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
    eyh
    -0.08
    eyJ
    -0.06
    eras
    -0.06
    czy
    -0.06
    anny
    -0.06
     Bilim
    -0.06
    aus
    -0.06
    744
    -0.06
    itur
    -0.05
     EntityState
    -0.05
    POSITIVE LOGITS
    sson
    0.07
    atform
    0.07
     Arb
    0.06
    åde
    0.06
    bu
    0.06
    __,__
    0.06
    gil
    0.06
    بÙĪاسطة
    0.06
    ight
    0.06
    ogen
    0.06
    Activations Density 0.010%

    No Known Activations