© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77024
    Prev
    Next
    INDEX
    Explanations

    timestamps and time-related information

    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
     Doyle
    -0.06
     Wat
    -0.06
    ierz
    -0.06
    ria
    -0.06
    emouth
    -0.06
     Date
    -0.06
    adel
    -0.06
    ÄĻ
    -0.06
    ock
    -0.06
     Ald
    -0.05
    POSITIVE LOGITS
    Ỽt
    0.07
    assing
    0.07
    earer
    0.07
    Rx
    0.07
     Uhr
    0.07
    unma
    0.07
    .IContainer
    0.07
    Ñģи
    0.07
     ëĸ¨ìĸ´
    0.07
    omorphic
    0.07
    Activations Density 0.057%

    No Known Activations