© 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. 61297
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting related to lists or sections in a document

    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
    igan
    -0.07
     Kostenlos
    -0.06
    eenth
    -0.06
    anan
    -0.06
    olly
    -0.06
    ollipop
    -0.06
    änge
    -0.06
    enek
    -0.06
     Lage
    -0.06
     giants
    -0.06
    POSITIVE LOGITS
    Slash
    0.06
    structions
    0.06
    oreach
    0.06
    637
    0.06
    overn
    0.06
    oner
    0.06
    еÑĢÑĤи
    0.06
    ади
    0.06
    OGLE
    0.06
    odied
    0.06
    Activations Density 0.003%

    No Known Activations