© 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. 119096
    Prev
    Next
    INDEX
    Explanations

    references to sacrifices or justifications for actions

    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
    ì°¨
    -0.07
    enz
    -0.06
    iedy
    -0.06
    POCH
    -0.06
    igure
    -0.06
    afen
    -0.06
     frequ
    -0.06
    eza
    -0.06
    poon
    -0.06
     cru
    -0.06
    POSITIVE LOGITS
     gain
    0.07
    uÄį
    0.07
     principle
    0.07
    /save
    0.07
    mere
    0.07
     Principle
    0.07
     McGr
    0.06
    κει
    0.06
    serter
    0.06
    egra
    0.06
    Activations Density 0.051%

    No Known Activations