© 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. 61955
    Prev
    Next
    INDEX
    Explanations

    variable and constant declarations in programming context

    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
    ero
    -0.07
    olo
    -0.06
    óz
    -0.06
    awa
    -0.06
    親
    -0.06
    oun
    -0.06
    ville
    -0.06
    تÙĬ
    -0.06
    icles
    -0.06
    à¹Ģหล
    -0.06
    POSITIVE LOGITS
    adia
    0.07
    interop
    0.07
    jedn
    0.06
    unger
    0.06
    ysi
    0.06
     defaultManager
    0.06
    .TAG
    0.06
    еÑĢж
    0.06
    pike
    0.06
     serialVersionUID
    0.06
    Activations Density 0.009%

    No Known Activations