© 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. 76932
    Prev
    Next
    INDEX
    Explanations

    phrases associated with military personnel and operations

    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
    ossier
    -0.06
    _Tis
    -0.06
    ussen
    -0.06
    -fill
    -0.06
    raquo
    -0.06
    .IsNullOr
    -0.06
     Onun
    -0.06
    ãģ«è¦ĭ
    -0.06
    ulers
    -0.06
    ãĥ¬ãĤ¹
    -0.06
    POSITIVE LOGITS
     next
    0.08
    -next
    0.07
     plans
    0.07
    next
    0.07
    ÛĮØ´
    0.06
     apparently
    0.06
    idot
    0.06
    igy
    0.06
     soon
    0.06
    rud
    0.06
    Activations Density 0.036%

    No Known Activations