© 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. 16075
    Prev
    Next
    INDEX
    Explanations

    expressions related to perseverance and continuation in the face of 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
     hood
    -0.07
    nim
    -0.07
    nick
    -0.06
    hood
    -0.06
    ssc
    -0.06
    leigh
    -0.06
    kir
    -0.06
    ç§Ģ
    -0.06
    лÑĥг
    -0.06
    uddle
    -0.06
    POSITIVE LOGITS
     legacy
    0.12
     continuation
    0.10
     Legacy
    0.09
     carrying
    0.09
     continuing
    0.09
    legacy
    0.09
     carry
    0.08
     continue
    0.08
    carry
    0.08
    herit
    0.08
    Activations Density 0.014%

    No Known Activations