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

    Neuronpedia

    Jacobian LensNEW
    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. 77134
    Prev
    Next
    INDEX
    Explanations

    technical details and parameters related to signal processing and path transmission in communication systems

    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
    ddy
    -0.07
    agem
    -0.07
    æij©
    -0.06
    _handlers
    -0.06
     ÑĤеÑĩ
    -0.06
    alarm
    -0.06
    _simps
    -0.06
    andler
    -0.06
    day
    -0.06
     modelName
    -0.06
    POSITIVE LOGITS
     receiver
    0.07
     Receiver
    0.07
     channel
    0.07
     receivers
    0.07
     ÄĮesko
    0.06
    .sky
    0.06
    _receiver
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
    çĿ
    0.06
     received
    0.06
    Activations Density 0.061%

    No Known Activations