© 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. 5-LLAMASCOPE-RES-131K
    11. 126970
    Prev
    Next
    INDEX
    Explanations

    references to direct communication or addressing the reader

    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
    arel
    -0.07
    âr
    -0.06
     kin
    -0.06
    view
    -0.06
    forward
    -0.06
    ¹Ħ
    -0.05
    unkt
    -0.05
    497
    -0.05
    termin
    -0.05
     Gang
    -0.05
    POSITIVE LOGITS
    ethyst
    0.07
    ResourceManager
    0.07
    statuses
    0.07
    idis
    0.07
    aghan
    0.07
    utr
    0.07
    ìķł
    0.07
    spiel
    0.07
     ØŃاصÙĦ
    0.07
    Vac
    0.07
    Activations Density 0.004%

    No Known Activations