© 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. 17-LLAMASCOPE-RES-131K
    11. 83677
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to events and entities

    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
    aper
    -0.06
     run
    -0.06
    urum
    -0.06
     retr
    -0.06
    942
    -0.06
     form
    -0.06
    MBER
    -0.06
    mlin
    -0.05
    itsu
    -0.05
     tail
    -0.05
    POSITIVE LOGITS
    Ñģклад
    0.08
    æ¥ļ
    0.07
    .Îł
    0.07
    .qual
    0.07
    owitz
    0.07
    asca
    0.07
    od
    0.07
    .spin
    0.07
     Circular
    0.07
    imuth
    0.07
    Activations Density 0.010%

    No Known Activations