© 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. 15-LLAMASCOPE-RES-131K
    6. 103349
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "it" in various contexts

    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
    ductive
    -0.07
    Äįi
    -0.06
    ellas
    -0.06
    oe
    -0.06
    py
    -0.06
    usk
    -0.06
    iously
    -0.06
    ox
    -0.06
    avenport
    -0.06
    actly
    -0.06
    POSITIVE LOGITS
    orem
    0.09
    šker
    0.09
    inerary
    0.09
    eview
    0.09
    oretical
    0.09
    linger
    0.08
    gnore
    0.08
    .IsAny
    0.08
    odore
    0.08
    oret
    0.08
    Activations Density 0.062%

    No Known Activations