© 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. 83880
    Prev
    Next
    INDEX
    Explanations

    terms indicating standardization and organization

    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
     Til
    -0.06
     Maz
    -0.06
    ansi
    -0.06
     ngu
    -0.06
     ï
    -0.06
    .BorderColor
    -0.05
     H
    -0.05
    --)
    -0.05
     Nel
    -0.05
    วล
    -0.05
    POSITIVE LOGITS
    bie
    0.08
    ÑĨин
    0.07
     Pazar
    0.07
     cadastr
    0.07
    simp
    0.07
    +++
    0.07
    ynch
    0.07
    iti
    0.06
     taky
    0.06
    @dynamic
    0.06
    Activations Density 0.046%

    No Known Activations