Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4386
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one"

    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
    scribe
    -0.09
    uffy
    -0.08
    theon
    -0.07
    velt
    -0.07
    ffffff
    -0.07
    arging
    -0.07
     Stevenson
    -0.07
    niest
    -0.06
    onda
    -0.06
    maal
    -0.06
    POSITIVE LOGITS
     handed
    0.07
     minded
    0.06
     eyed
    0.06
    addock
    0.06
    iston
    0.06
    -of
    0.05
    ir
    0.05
     liners
    0.05
     single
    0.05
     dimensional
    0.05
    Activations Density 0.038%

    No Known Activations