INDEX

Explanations

programming language keywords and educational terms related to guidelines and standards

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 JÃ¡

-0.16

enstein

-0.16

nam

-0.14

ofil

-0.14

Nam

-0.14

uzzi

-0.14

cka

-0.13

dbo

-0.13

ikes

-0.13

ãĥ¼ãĥĪ

-0.13

POSITIVE LOGITS

oven

0.16

olph

0.16

jury

0.15

 directly

0.15

@}

0.15

dech

0.14

ibble

0.14

 ç¾

0.14

gsi

0.14

Activations Density 0.013%

programming language keywords and educational terms related to guidelines and standards

No Known Activations