Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96013
    Prev
    Next
    INDEX
    Explanations

    numerical values in a code-related 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
    lemen
    -0.08
    еÑĩ
    -0.07
    lemn
    -0.07
    olson
    -0.07
    thon
    -0.06
     hete
    -0.06
    935
    -0.06
    emouth
    -0.06
    naments
    -0.06
    ë³
    -0.06
    POSITIVE LOGITS
    ITY
    0.07
    ity
    0.07
    zeit
    0.06
    Ñĩив
    0.06
     IGN
    0.06
    ì±Ħ
    0.06
    zahl
    0.06
    emsp
    0.06
     Dai
    0.06
    recision
    0.05
    Activations Density 0.024%

    No Known Activations