© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 13-LLAMASCOPE-RES-32K
    11. 26268
    Prev
    Next
    INDEX
    Explanations

    terms related to objects and parameters used in software or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    หลวà¸ĩ
    -0.15
    à¸ļà¸Ħ
    -0.14
    arta
    -0.14
    ostat
    -0.14
    urtle
    -0.14
    οÏįν
    -0.14
    trap
    -0.13
    aper
    -0.13
    erra
    -0.13
     exchange
    -0.13
    POSITIVE LOGITS
    eof
    0.14
    701
    0.14
    ders
    0.14
     seiz
    0.14
    illez
    0.14
    ãĥ©ãĤ¤
    0.14
    ance
    0.14
     повÑĸÑĤ
    0.14
    inizi
    0.14
    Tower
    0.14
    Activations Density 0.003%

    No Known Activations