© 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. 128696
    Prev
    Next
    INDEX
    Explanations

    objects and structures that provide safety or support in various contexts

    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
     hopefully
    -0.08
    ipa
    -0.07
    izr
    -0.07
    inke
    -0.07
    zas
    -0.07
    hopefully
    -0.07
    Whenever
    -0.07
    ILT
    -0.07
     whenever
    -0.07
     åIJ
    -0.06
    POSITIVE LOGITS
     nor
    0.14
     or
    0.10
     anymore
    0.08
     anywhere
    0.08
     oder
    0.08
     ani
    0.07
    nor
    0.07
     eller
    0.07
     nebo
    0.07
     ni
    0.07
    Activations Density 0.030%

    No Known Activations