© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105755
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to large-scale concepts or entities

    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
    thing
    -0.07
    iaux
    -0.07
    rary
    -0.07
    صÙĩ
    -0.07
    ouro
    -0.06
    ral
    -0.06
    sert
    -0.06
     ราà¸Ħ
    -0.06
     slight
    -0.06
    _ATTACHMENT
    -0.06
    POSITIVE LOGITS
    -scale
    0.20
     scale
    0.11
     enough
    0.10
    scale
    0.10
    Scale
    0.09
     amounts
    0.09
    -format
    0.09
    -hearted
    0.09
    /small
    0.09
     Scale
    0.09
    Activations Density 0.042%

    No Known Activations