© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    references to significant or impactful public figures and events

    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
    LookAndFeel
    -0.07
     Cop
    -0.06
    alist
    -0.06
     ('
    -0.06
    à¥įसर
    -0.06
    isbury
    -0.06
    gili
    -0.06
    benh
    -0.06
    æ¡
    -0.06
    cop
    -0.06
    POSITIVE LOGITS
     aged
    0.21
     age
    0.20
    -aged
    0.17
     Age
    0.16
    age
    0.16
    aged
    0.15
     ages
    0.15
    -age
    0.15
    .age
    0.15
    å¹´é¾Ħ
    0.15
    Activations Density 0.185%

    No Known Activations