© 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. 126284
    Prev
    Next
    INDEX
    Explanations

    details about payment and delivery services

    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
    owl
    -0.08
    loi
    -0.07
    undi
    -0.07
     NotImplemented
    -0.07
    xDE
    -0.06
    å¹¹ç·ļ
    -0.06
    ạnh
    -0.06
    .cf
    -0.06
    imits
    -0.06
    .owl
    -0.06
    POSITIVE LOGITS
     delivery
    0.08
     Delivery
    0.08
    oken
    0.07
    nech
    0.07
     deliveries
    0.07
     door
    0.07
     ker
    0.07
     Door
    0.07
    Door
    0.07
    ltk
    0.06
    Activations Density 0.017%

    No Known Activations