© 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. 3875
    Prev
    Next
    INDEX
    Explanations

    terms related to disasters and emergencies

    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
    rit
    -0.08
    issen
    -0.06
     aras
    -0.06
    ec
    -0.06
    isle
    -0.06
     Lös
    -0.06
    asper
    -0.06
     Sah
    -0.06
    uye
    -0.06
    Ñij
    -0.06
    POSITIVE LOGITS
    edl
    0.09
     such
    0.07
    such
    0.07
     situations
    0.07
    _Lean
    0.07
     affecting
    0.07
    Latch
    0.07
    unga
    0.07
    Such
    0.07
     situation
    0.07
    Activations Density 0.022%

    No Known Activations