© 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. 16284
    Prev
    Next
    INDEX
    Explanations

    expressions related to value and inequality

    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
    .springboot
    -0.07
    ocator
    -0.07
    eneg
    -0.06
    esel
    -0.06
    enuine
    -0.06
     scop
    -0.06
    nels
    -0.06
     Engl
    -0.06
    ocy
    -0.06
    pta
    -0.06
    POSITIVE LOGITS
    emek
    0.07
    imler
    0.07
    verte
    0.07
    بار
    0.06
    .ret
    0.06
    кÑĤа
    0.06
     جÙħع
    0.06
    .mdl
    0.06
    oola
    0.06
     اÙĦÙĤر
    0.06
    Activations Density 0.000%

    No Known Activations