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

    Neuronpedia

    Jacobian LensNEW
    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. 87469
    Prev
    Next
    INDEX
    Explanations

    terms related to support, restoration, and rescue efforts for various situations and entities

    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
    IRR
    -0.07
     irony
    -0.07
     irrelevant
    -0.06
    олод
    -0.06
     Worse
    -0.06
    CCR
    -0.06
     slows
    -0.06
    ãģķãĤī
    -0.06
    DMI
    -0.06
    éļ
    -0.06
    POSITIVE LOGITS
     lost
    0.10
    lost
    0.09
     otherwise
    0.08
     endangered
    0.08
     egreg
    0.08
     fal
    0.08
     Lost
    0.08
    angered
    0.07
     missed
    0.07
     whose
    0.07
    Activations Density 0.244%

    No Known Activations