© 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. 9-LLAMASCOPE-RES-131K
    11. 95767
    Prev
    Next
    INDEX
    Explanations

    requests for improved quality and diversity in content or processes

    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
    Ìģ
    -0.08
    asz
    -0.06
    ErrorException
    -0.06
    autor
    -0.06
     pij
    -0.06
    iverse
    -0.06
    KF
    -0.06
     Autor
    -0.06
    ael
    -0.06
     lyon
    -0.06
    POSITIVE LOGITS
    .RadioButton
    0.07
    etik
    0.07
    awah
    0.07
    ceae
    0.06
    zell
    0.06
    OLEAN
    0.06
    egra
    0.06
    isser
    0.06
    auga
    0.06
    å²Ĺ
    0.06
    Activations Density 0.014%

    No Known Activations