© 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. 15-LLAMASCOPE-RES-131K
    11. 62564
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the state of being unknown or unnoticed

    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
    iese
    -0.09
    SSIP
    -0.08
    ména
    -0.07
    illian
    -0.07
    izi
    -0.07
    ucha
    -0.07
    phies
    -0.07
    tron
    -0.07
    åĩ
    -0.07
    izations
    -0.06
    POSITIVE LOGITS
    ingly
    0.08
    VF
    0.06
     Hollow
    0.06
    ì¤Ħ
    0.06
    etest
    0.05
    sdale
    0.05
    ep
    0.05
     Brace
    0.05
     GH
    0.05
    ensa
    0.05
    Activations Density 0.002%

    No Known Activations