© 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. 70933
    Prev
    Next
    INDEX
    Explanations

    references to political accusations and formal statements

    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
    ãĤ¦ãĥ³
    -0.09
    аÑĢам
    -0.08
    елик
    -0.08
    UrlParser
    -0.08
    ichert
    -0.08
     ciz
    -0.08
    erdale
    -0.07
    PTS
    -0.07
     @$_
    -0.07
    iffs
    -0.07
    POSITIVE LOGITS
     former
    0.14
     Former
    0.11
    Former
    0.09
    former
    0.09
     retired
    0.07
     current
    0.07
    0.07
    ³
    0.07
     Ven
    0.07
    Ven
    0.06
    Activations Density 0.103%

    No Known Activations