Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4384
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connecting words in sentences

    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
    inium
    -0.08
    @dynamic
    -0.07
    нÑĮ
    -0.07
    buie
    -0.07
    ä¸įå¾Ĺ
    -0.07
    BuilderInterface
    -0.07
    allon
    -0.07
    achi
    -0.07
    HIR
    -0.06
    yang
    -0.06
    POSITIVE LOGITS
     provide
    0.12
     offer
    0.11
     help
    0.10
    provide
    0.10
     Provide
    0.10
     provides
    0.10
     answer
    0.09
    æıIJä¾Ľ
    0.09
    帮
    0.09
     will
    0.09
    Activations Density 0.025%

    No Known Activations