© 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. 23-LLAMASCOPE-RES-32K
    11. 1025
    Prev
    Next
    INDEX
    Explanations

    phrases related to product durability and strength

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichert
    -0.15
    enheim
    -0.14
     fizz
    -0.14
     Ding
    -0.14
    ekl
    -0.14
    anz
    -0.14
    .bias
    -0.13
    ìĽĶë¶ĢíĦ°
    -0.13
    otten
    -0.13
    åĬ¿
    -0.13
    POSITIVE LOGITS
     withstand
    0.38
     hold
    0.34
     stand
    0.33
     stood
    0.33
     holds
    0.32
     holding
    0.31
     stands
    0.30
     Holds
    0.29
    stood
    0.29
     survive
    0.28
    Activations Density 0.180%

    No Known Activations