© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88121
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "much."

    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
    asser
    -0.08
    ersive
    -0.06
    conc
    -0.06
    icut
    -0.06
     nonatomic
    -0.06
     knack
    -0.06
     conc
    -0.06
    urovision
    -0.06
    elian
    -0.06
     Are
    -0.06
    POSITIVE LOGITS
     ado
    0.10
    acha
    0.08
    ington
    0.07
    -needed
    0.07
    ibu
    0.07
    acho
    0.07
     Portions
    0.07
     portions
    0.07
    adr
    0.07
    urma
    0.07
    Activations Density 0.025%

    No Known Activations