© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95059
    Prev
    Next
    INDEX
    Explanations

    references to data and resources related to climate information

    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
     male
    -0.06
     so
    -0.06
     adult
    -0.06
    A
    -0.05
     g
    -0.05
     oper
    -0.05
    ;
    -0.05
     Roberts
    -0.05
    hev
    -0.05
     a
    -0.05
    POSITIVE LOGITS
    زÙĩ
    0.08
     ãĤ¢ãĤ¤
    0.08
    isque
    0.08
    ERRU
    0.08
    ocht
    0.08
    _BINDING
    0.07
    ì¦Ī
    0.07
    aska
    0.07
    _DH
    0.07
    ÑĤÑĢо
    0.07
    Activations Density 0.028%

    No Known Activations