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. 4-LLAMASCOPE-RES-32K
    6. 26698
    Prev
    Next
    INDEX
    Explanations

    expressions questioning reasons or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    боÑĤ
    -0.14
    ighth
    -0.14
    åĬ¿
    -0.14
     Amb
    -0.14
    ajo
    -0.14
     amb
    -0.14
    ERRU
    -0.14
    vection
    -0.14
    raig
    -0.14
    gnu
    -0.14
    POSITIVE LOGITS
    ctal
    0.17
    ;display
    0.15
    tres
    0.15
    edik
    0.14
    QWidget
    0.14
    egin
    0.13
    696
    0.13
    ulty
    0.13
    ibli
    0.13
    æĹ¥
    0.13
    Activations Density 0.013%

    No Known Activations