© 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. 126771
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and operations

    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
     McGu
    -0.06
     Frost
    -0.06
    lop
    -0.06
    ÑĨо
    -0.06
    rier
    -0.06
    odie
    -0.06
     than
    -0.06
     McCoy
    -0.06
    ft
    -0.06
     rather
    -0.06
    POSITIVE LOGITS
    .inspect
    0.08
    anela
    0.08
    istrovstvÃŃ
    0.07
    LOCKS
    0.07
    ανά
    0.07
     ENTITY
    0.06
    andest
    0.06
    _png
    0.06
    Subscription
    0.06
     Sokol
    0.06
    Activations Density 0.023%

    No Known Activations