© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62242
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information related to events or timelines

    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
    urn
    -0.06
     overall
    -0.06
    acock
    -0.06
    nob
    -0.06
     haus
    -0.06
     Yer
    -0.06
     inter
    -0.06
    INCREMENT
    -0.06
    è¼Ŀ
    -0.05
    _outer
    -0.05
    POSITIVE LOGITS
    ignon
    0.08
    ledged
    0.07
    alla
    0.07
    oma
    0.07
    ạ
    0.06
     âĢª
    0.06
    £
    0.06
    ordin
    0.06
    TA
    0.06
    erializer
    0.06
    Activations Density 0.036%

    No Known Activations