INDEX

Explanations

references to programming errors and handling exceptions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ollen

-0.16

adio

-0.15

aceut

-0.14

ECH

-0.14

 nominal

-0.14

anton

-0.13

onaut

-0.13

lus

-0.13

ault

-0.13

POSITIVE LOGITS

yd

0.15

ROC

0.15

åĢĻ

0.14

äº«

0.14

profits

0.14

 Oaks

0.13

opus

0.13

untu

0.13

Ø¯Ø§ÙĨÙĦÙĪØ¯

0.13

ither

0.13

Activations Density 0.121%

references to programming errors and handling exceptions in code

No Comments

No Known Activations