© 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. 57263
    Prev
    Next
    INDEX
    Explanations

    references to former officials or people in authoritative positions

    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
    uild
    -0.07
    emouth
    -0.07
    avel
    -0.07
    tiv
    -0.07
    reich
    -0.06
    roat
    -0.06
    ynet
    -0.06
    extends
    -0.06
    iti
    -0.06
    annes
    -0.06
    POSITIVE LOGITS
     former
    0.08
    kke
    0.07
     ex
    0.07
     rep
    0.06
     partners
    0.06
     erst
    0.06
     Former
    0.06
    crest
    0.06
    ively
    0.06
    .libs
    0.06
    Activations Density 0.013%

    No Known Activations