© 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. 15-LLAMASCOPE-RES-131K
    11. 90576
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement and support

    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
    ront
    -0.07
    antt
    -0.07
    ç½
    -0.06
    rente
    -0.06
     cus
    -0.06
    еко
    -0.05
    ile
    -0.05
    ç´Ģ
    -0.05
    endoza
    -0.05
    ersen
    -0.05
    POSITIVE LOGITS
    unsch
    0.08
    .mixin
    0.07
    ноÑģ
    0.07
    fulness
    0.07
    .SC
    0.07
    ines
    0.07
     prostÅĻednictvÃŃm
    0.07
    jedn
    0.07
    ære
    0.06
    enheim
    0.06
    Activations Density 0.025%

    No Known Activations