© 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. 57270
    Prev
    Next
    INDEX
    Explanations

    programming terms related to function calls and positional adjustments

    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
    ccoli
    -0.07
     Hind
    -0.07
    assi
    -0.06
    ErrorHandler
    -0.06
    帽
    -0.06
    aman
    -0.06
    assin
    -0.06
     ;;↵
    -0.06
    EqualTo
    -0.06
    ấu
    -0.06
    POSITIVE LOGITS
    :
    0.07
    yms
    0.06
     invoked
    0.06
    ():
    0.06
     proliferation
    0.06
    dech
    0.06
    etAddress
    0.06
     nbytes
    0.05
    731
    0.05
    ilent
    0.05
    Activations Density 0.021%

    No Known Activations