Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 13-LLAMASCOPE-RES-32K
    6. 16515
    Prev
    Next
    INDEX
    Explanations

    phrases indicating numerical or quantitative relationships, particularly in context with people and entities

    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
    UrlParser
    -0.17
    Å¡tÄĽ
    -0.15
    bsolute
    -0.14
    WriteBarrier
    -0.14
     kli
    -0.14
    _QMARK
    -0.14
    bridge
    -0.14
     æĻ´
    -0.14
    andro
    -0.14
    lor
    -0.13
    POSITIVE LOGITS
     or
    0.18
     Tou
    0.17
     either
    0.17
     oder
    0.17
    rank
    0.15
    oi
    0.15
     اÙĦÙĨÙĩ
    0.14
    -нибÑĥдÑĮ
    0.14
    od
    0.14
    CLK
    0.14
    Activations Density 0.205%

    No Known Activations