© 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. 82702
    Prev
    Next
    INDEX
    Explanations

    parameters and steps related to recipe preparation

    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
    _WP
    -0.07
    ãĥĥãĥĪ
    -0.06
    kup
    -0.06
     cánh
    -0.06
    ény
    -0.06
    hread
    -0.06
     abbreviated
    -0.06
    ulis
    -0.06
    usz
    -0.06
    à¹Īำ
    -0.06
    POSITIVE LOGITS
     add
    0.17
     adding
    0.17
     added
    0.15
    æ·»åĬł
    0.15
     adds
    0.15
     thêm
    0.15
     добав
    0.15
     Adding
    0.15
     Add
    0.15
     addition
    0.15
    Activations Density 0.112%

    No Known Activations