INDEX

Explanations

code-related terminology and functions within programming

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mason

-0.15

_simps

-0.15

 storm

-0.14

ãĤ¿ãĥ¼

-0.14

_Exception

-0.14

Storm

-0.14

 Storm

-0.14

 Chemistry

-0.14

oreach

-0.14

Äįka

-0.14

POSITIVE LOGITS

 tensor

0.28

Tensor

0.28

 tensorflow

0.28

 TensorFlow

0.27

tensorflow

0.27

 Tensor

0.26

 tensors

0.26

Tf

0.26

 absl

0.24

Op

0.24

Activations Density 0.007%

code-related terminology and functions within programming

No Comments

No Known Activations