© 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. 71887
    Prev
    Next
    INDEX
    Explanations

    structured data formats, particularly those that include references or citations

    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
    HITE
    -0.07
    hora
    -0.07
    gre
    -0.07
    rat
    -0.06
    iso
    -0.06
    lcd
    -0.06
    697
    -0.06
    les
    -0.06
    lit
    -0.05
    ombo
    -0.05
    POSITIVE LOGITS
     integral
    0.07
    ieber
    0.07
    agner
    0.07
    аниÑĨ
    0.07
    à¹Ģหล
    0.07
    ãn
    0.07
    .EventHandler
    0.07
    ãĥ¼ãĥĭ
    0.06
    (strpos
    0.06
     Sheridan
    0.06
    Activations Density 0.003%

    No Known Activations