Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96019
    Prev
    Next
    INDEX
    Explanations

    technical terms and syntax elements related to programming or coding logic

    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
    ceased
    -0.09
    venes
    -0.08
    夫
    -0.08
    reon
    -0.07
    žel
    -0.07
    Å¡tÃŃ
    -0.07
    FromBody
    -0.07
    omb
    -0.07
    ató
    -0.07
     Ipsum
    -0.07
    POSITIVE LOGITS
    uro
    0.06
     Gilles
    0.06
    วà¸Ļ
    0.06
     wax
    0.05
    gi
    0.05
     de
    0.05
     Wage
    0.05
    ky
    0.05
    ped
    0.05
     Bent
    0.05
    Activations Density 0.006%

    No Known Activations