© 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. 82562
    Prev
    Next
    INDEX
    Explanations

    phrases indicating complexity and multifaceted issues

    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
    uw
    -0.07
    à¥Įत
    -0.07
    FLT
    -0.06
    eam
    -0.06
     дÑĢÑĥгого
    -0.06
     вдÑĢÑĥг
    -0.06
    _means
    -0.06
    orp
    -0.06
    _na
    -0.06
    ÙĨاÙĨ
    -0.06
    POSITIVE LOGITS
     mostly
    0.20
    mostly
    0.18
     mainly
    0.16
     Mostly
    0.14
     primarily
    0.14
     largely
    0.14
     partly
    0.13
     principalmente
    0.13
    主è¦ģ
    0.12
     оÑģновном
    0.11
    Activations Density 0.099%

    No Known Activations