© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75557
    Prev
    Next
    INDEX
    Explanations

    sources of guidance and support, particularly in challenging situations

    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
    infeld
    -0.07
    SingleNode
    -0.07
    cak
    -0.07
    prak
    -0.07
    .scala
    -0.07
    lement
    -0.07
    flen
    -0.07
    enga
    -0.07
    obec
    -0.07
     بÙĨدÛĮ
    -0.06
    POSITIVE LOGITS
     reliance
    0.12
     resort
    0.12
     rely
    0.11
     relied
    0.11
     recourse
    0.11
    éł¼
    0.10
     seeking
    0.09
     dependence
    0.09
     relies
    0.09
     resorts
    0.09
    Activations Density 0.118%

    No Known Activations