© 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. 55891
    Prev
    Next
    INDEX
    Explanations

    phrases indicating value, worth, or effort

    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
    ungle
    -0.08
    elop
    -0.07
     modal
    -0.07
    otte
    -0.07
    Äįet
    -0.07
    ulate
    -0.07
     ÑĤабли
    -0.07
     Whe
    -0.07
    portlet
    -0.07
    ãģĻãģĻ
    -0.07
    POSITIVE LOGITS
     effort
    0.10
     investment
    0.07
     risk
    0.07
     bother
    0.06
     invested
    0.06
    ummings
    0.06
     explosive
    0.06
     sacrifice
    0.06
    Bootstrap
    0.06
    Invest
    0.06
    Activations Density 0.005%

    No Known Activations