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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80005
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and its variations

    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
     odds
    -0.05
     certain
    -0.05
    aise
    -0.05
    assen
    -0.05
    etic
    -0.05
     Mey
    -0.05
     Ren
    -0.05
    arsed
    -0.05
    atan
    -0.05
    ``↵
    -0.05
    POSITIVE LOGITS
    âĺħ
    0.07
    iesen
    0.07
     term
    0.07
    ħn
    0.07
    odem
    0.07
    unsch
    0.07
    âĺħâĺħ
    0.07
    leme
    0.07
    illet
    0.07
    ÑĤин
    0.07
    Activations Density 0.022%

    No Known Activations