© 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. 9-LLAMASCOPE-RES-131K
    11. 95788
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" and variations of the word "a"

    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
    apesh
    -0.08
    istra
    -0.08
    geber
    -0.07
     somehow
    -0.07
    undy
    -0.07
    /epl
    -0.07
    uggage
    -0.07
    timeofday
    -0.07
    .minecraft
    -0.06
    nt
    -0.06
    POSITIVE LOGITS
    ivr
    0.06
     considerable
    0.06
    ÙĤب
    0.06
    owell
    0.06
    PIN
    0.06
     gad
    0.06
    .False
    0.06
    ©
    0.06
    isos
    0.06
     ITE
    0.06
    Activations Density 0.004%

    No Known Activations