© 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. 29-LLAMASCOPE-RES-32K
    11. 15722
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and provinces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸ŀระราà¸Ĭ
    -0.15
     Byl
    -0.14
    eket
    -0.14
     nations
    -0.14
    agli
    -0.13
    åľĭ家
    -0.13
    wolf
    -0.13
    otel
    -0.13
    oger
    -0.13
    -mult
    -0.13
    POSITIVE LOGITS
     province
    0.71
     Province
    0.64
    province
    0.51
    çľģ
    0.50
    Province
    0.50
     provinces
    0.40
     provinc
    0.40
     provincia
    0.39
     provincial
    0.38
    _province
    0.35
    Activations Density 0.101%

    No Known Activations