© 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. 77647
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "change."

    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
    AKE
    -0.07
    ness
    -0.07
    lut
    -0.07
    ms
    -0.07
    ake
    -0.07
    rome
    -0.07
    AILS
    -0.07
    riday
    -0.07
     treff
    -0.07
    lide
    -0.06
    POSITIVE LOGITS
    ability
    0.08
    over
    0.08
    vic
    0.07
    able
    0.07
     change
    0.06
    urs
    0.06
     Change
    0.06
    -change
    0.06
     chang
    0.06
    urum
    0.06
    Activations Density 0.014%

    No Known Activations