© 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. 128732
    Prev
    Next
    INDEX
    Explanations

    phrases related to safe and supportive environments

    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
    ntl
    -0.08
    izmet
    -0.06
    urses
    -0.06
    emand
    -0.06
    анÑģи
    -0.06
    rani
    -0.06
    ila
    -0.06
    ottle
    -0.06
    qua
    -0.06
    ?f
    -0.06
    POSITIVE LOGITS
     environment
    0.14
     atmosphere
    0.13
     environments
    0.12
     atmos
    0.12
     ortam
    0.10
     аÑĤмоÑģ
    0.10
     Environment
    0.10
     conditions
    0.10
     ambiente
    0.10
     Atmos
    0.09
    Activations Density 0.025%

    No Known Activations