© 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. 17-LLAMASCOPE-RES-131K
    11. 107220
    Prev
    Next
    INDEX
    Explanations

    references to authors and their works or achievements

    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
    tura
    -0.06
     circumstance
    -0.06
     Nobel
    -0.06
     Eudicots
    -0.06
    аÑĢод
    -0.06
    gradable
    -0.06
    ominated
    -0.06
    ombre
    -0.06
    olis
    -0.06
     theirs
    -0.06
    POSITIVE LOGITS
     latest
    0.08
    û
    0.08
     recently
    0.07
     اÙĦتÙĤ
    0.07
     other
    0.07
     next
    0.07
    next
    0.07
    .Xaml
    0.07
     newest
    0.07
    latest
    0.07
    Activations Density 0.010%

    No Known Activations