© 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. 5-LLAMASCOPE-RES-131K
    6. 126990
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "by" 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
    zman
    -0.07
    rosso
    -0.07
    abler
    -0.06
    zano
    -0.06
    æ·¡
    -0.06
    ove
    -0.06
    hei
    -0.06
    oble
    -0.06
    star
    -0.06
    lix
    -0.06
    POSITIVE LOGITS
    -avatar
    0.07
    _TUN
    0.06
    âĶĶ
    0.06
    IMS
    0.06
    _overlay
    0.06
    訳
    0.06
    thr
    0.06
    minster
    0.06
     ÑĢок
    0.06
    ChildIndex
    0.05
    Activations Density 0.002%

    No Known Activations