© 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. 106245
    Prev
    Next
    INDEX
    Explanations

    references to historical events or timelines

    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
     currently
    -0.09
    yet
    -0.09
    缮åīį
    -0.09
    currently
    -0.08
    heid
    -0.08
     yet
    -0.08
    indr
    -0.07
     current
    -0.07
    ixin
    -0.07
     bisher
    -0.07
    POSITIVE LOGITS
     merely
    0.07
    OLLOW
    0.06
     when
    0.06
     whenever
    0.06
    kü
    0.06
     Fallon
    0.06
     ok
    0.06
    ãĥ³ãĥĶ
    0.06
     simply
    0.06
    (before
    0.06
    Activations Density 0.025%

    No Known Activations