© 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. 125907
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and systemic challenges

    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±ãĥĥãĥĪ
    -0.08
    nnen
    -0.07
    783
    -0.07
    774
    -0.07
    ninger
    -0.07
    åīĽ
    -0.06
    akov
    -0.06
    822
    -0.06
    æŁĵ
    -0.06
    تÙĦ
    -0.06
    POSITIVE LOGITS
     Defense
    0.07
     defence
    0.07
     Defence
    0.07
     defense
    0.07
     cliff
    0.07
     getDefault
    0.07
     Ashton
    0.06
    ownt
    0.06
    cq
    0.06
    opa
    0.06
    Activations Density 0.001%

    No Known Activations