© 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. 15-LLAMASCOPE-RES-131K
    11. 89953
    Prev
    Next
    INDEX
    Explanations

    references to specific children's literature and the associated plot elements

    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
    /REC
    -0.07
    lesh
    -0.07
    asso
    -0.06
    rego
    -0.06
     *\
    -0.06
     Lâm
    -0.06
    .AutoComplete
    -0.06
     headlights
    -0.06
    olet
    -0.06
    .substr
    -0.06
    POSITIVE LOGITS
    êµ´
    0.07
    angl
    0.06
    	children
    0.06
     gan
    0.06
    geist
    0.06
     Trident
    0.06
     children
    0.06
    èĢIJ
    0.06
     Pied
    0.06
     Children
    0.06
    Activations Density 0.001%

    No Known Activations