© 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. 105853
    Prev
    Next
    INDEX
    Explanations

    instances of the word "full," particularly when indicating abundance or completion

    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
    oggler
    -0.07
    ect
    -0.07
    em
    -0.07
    emer
    -0.07
    ë£
    -0.06
    SURE
    -0.06
    reck
    -0.06
    off
    -0.06
    antage
    -0.06
     å
    -0.06
    POSITIVE LOGITS
    filled
    0.09
    fill
    0.08
     of
    0.08
    fills
    0.07
    بار
    0.07
    tright
    0.07
    566
    0.06
    uously
    0.06
    gesi
    0.06
    yang
    0.06
    Activations Density 0.007%

    No Known Activations