© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127006
    Prev
    Next
    INDEX
    Explanations

    instances of linguistic connectors and references to cited works

    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
    addle
    -0.08
    ridge
    -0.07
    mans
    -0.06
    bench
    -0.06
     cass
    -0.06
    妮
    -0.06
    ends
    -0.06
    æĹ¶åĢĻ
    -0.06
     bes
    -0.06
    TC
    -0.05
    POSITIVE LOGITS
     references
    0.09
    references
    0.09
     дÑĢ
    0.07
    DRAM
    0.07
     its
    0.07
    OfYear
    0.07
     earlier
    0.07
     others
    0.06
     comple
    0.06
    @nate
    0.06
    Activations Density 0.023%

    No Known Activations