© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1214
    Prev
    Next
    INDEX
    Explanations

    phrases discussing statistical measures and their implications

    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
     inversion
    -0.06
    018
    -0.06
     anim
    -0.06
     наз
    -0.06
     Hatch
    -0.06
     icon
    -0.05
     modification
    -0.05
     for
    -0.05
     reversal
    -0.05
    hani
    -0.05
    POSITIVE LOGITS
    elman
    0.09
    км
    0.07
    çıł
    0.07
     vypl
    0.07
    unwrap
    0.07
     Reporting
    0.07
    Reporting
    0.07
    ody
    0.07
     addCriterion
    0.07
    SetActive
    0.07
    Activations Density 0.051%

    No Known Activations