© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27219
    Prev
    Next
    INDEX
    Explanations

    mentions of fruit or references to quantity and attributes of items

    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
    uth
    -0.07
    #
    -0.06
    ilia
    -0.06
    elle
    -0.06
    ť
    -0.06
    wer
    -0.06
     authority
    -0.06
    ander
    -0.06
    UTH
    -0.06
    ropa
    -0.06
    POSITIVE LOGITS
    ieri
    0.08
    ,[],
    0.07
    celik
    0.07
    ikk
    0.06
     mart
    0.06
    ÃŃsto
    0.06
    ä¹ĭä¸Ģ
    0.06
    779
    0.06
     martin
    0.06
    qml
    0.06
    Activations Density 0.007%

    No Known Activations