© 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. 3929
    Prev
    Next
    INDEX
    Explanations

    references to people or entities involved in software licensing or legal contexts

    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
    zon
    -0.07
    iers
    -0.06
    ureau
    -0.06
    hei
    -0.06
    kea
    -0.06
     Wing
    -0.06
    æŁĦ
    -0.06
    ernals
    -0.06
    duc
    -0.06
     inform
    -0.05
    POSITIVE LOGITS
     einf
    0.07
    fel
    0.06
    NU
    0.06
     Pearl
    0.06
    碰
    0.06
     Regions
    0.06
    .writeln
    0.06
    anter
    0.06
     Vern
    0.06
     RAT
    0.06
    Activations Density 0.000%

    No Known Activations