© 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. 17156
    Prev
    Next
    INDEX
    Explanations

    concepts related to physical processes and mechanisms

    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
     Labor
    -0.07
    mess
    -0.06
     devoted
    -0.06
    edith
    -0.06
    410
    -0.06
    иÑĤоÑĢ
    -0.06
    inth
    -0.06
     rele
    -0.06
    estre
    -0.06
     bot
    -0.06
    POSITIVE LOGITS
    .SDK
    0.07
     æĵ
    0.07
     Entr
    0.07
     Cav
    0.07
    STREAM
    0.07
     æ¹
    0.07
    Marsh
    0.07
     Converted
    0.07
     Plasma
    0.07
    oyer
    0.07
    Activations Density 0.012%

    No Known Activations