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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128497
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    .scalablytyped
    -0.08
    ternet
    -0.08
    ãģıãģł
    -0.08
    OMPI
    -0.08
    addir
    -0.07
     UNIVERS
    -0.07
    abbreviation
    -0.07
    imdi
    -0.07
    lez
    -0.07
    ampions
    -0.07
    POSITIVE LOGITS
     solutions
    0.06
     solution
    0.06
     Us
    0.06
    ogie
    0.06
    alo
    0.06
     se
    0.05
    _nt
    0.05
     Anast
    0.05
     variables
    0.05
     _
    0.05
    Activations Density 0.057%

    No Known Activations