© 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. 79144
    Prev
    Next
    INDEX
    Explanations

    instances of temporal references

    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
    PEAR
    -0.07
    Destructor
    -0.07
    arrant
    -0.07
    baum
    -0.06
    icode
    -0.06
    sonian
    -0.06
     sign
    -0.06
    urdy
    -0.06
    ance
    -0.06
    thead
    -0.06
    POSITIVE LOGITS
    TO
    0.07
    ialis
    0.06
    ;.
    0.06
    removeAttr
    0.06
    APT
    0.06
     तà¤ķ
    0.06
     문
    0.06
    æ¼ı
    0.06
    IFO
    0.06
    akan
    0.06
    Activations Density 0.028%

    No Known Activations