© 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. 5-LLAMASCOPE-RES-131K
    11. 126016
    Prev
    Next
    INDEX
    Explanations

    terms related to plugin management and resource loading in programming

    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
    plusplus
    -0.07
    bers
    -0.07
     Chris
    -0.06
    Chris
    -0.06
    imenti
    -0.06
    ghest
    -0.06
    markup
    -0.06
     serge
    -0.06
    upuncture
    -0.06
    uma
    -0.06
    POSITIVE LOGITS
    CString
    0.07
    æĪ
    0.07
    agram
    0.06
     Garr
    0.06
     æ±
    0.06
    VR
    0.06
    orex
    0.06
    _UNSIGNED
    0.06
    uki
    0.06
     tre
    0.05
    Activations Density 0.017%

    No Known Activations