© 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. 22-LLAMASCOPE-RES-131K
    11. 4317
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords indicating package definitions and functionality

    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
    889
    -0.06
    .cmb
    -0.06
     ÙĨص
    -0.06
    _firestore
    -0.06
    FilterWhere
    -0.06
    iggers
    -0.06
    omon
    -0.06
     slopes
    -0.06
     Bölüm
    -0.06
     è«
    -0.05
    POSITIVE LOGITS
    ulle
    0.07
    ullo
    0.07
    ISK
    0.07
    amak
    0.07
    ivate
    0.07
     Scaffold
    0.06
    czas
    0.06
    aÄĩ
    0.06
    ħ§
    0.06
    arto
    0.06
    Activations Density 0.000%

    No Known Activations