© 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. 25-LLAMASCOPE-RES-32K
    11. 15871
    Prev
    Next
    INDEX
    Explanations

    references to language learning and multilingual communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aurant
    -0.15
     MIPS
    -0.14
    elm
    -0.14
     Grades
    -0.14
     Definitions
    -0.14
    erged
    -0.14
    ajs
    -0.14
     Loud
    -0.14
     Hed
    -0.14
    ipse
    -0.14
    POSITIVE LOGITS
     language
    0.60
     languages
    0.54
    language
    0.50
    è¯Ńè¨Ģ
    0.48
     lang
    0.48
     Language
    0.47
    languages
    0.44
    Language
    0.44
    _language
    0.42
     langue
    0.42
    Activations Density 0.106%

    No Known Activations