INDEX

Explanations

programming-related comments that indicate tasks or improvements needed in the 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

quer

-0.15

undler

-0.14

IBUTES

-0.14

"><!--

-0.13

rema

-0.13

âĢ¦"↵↵

-0.13

ï¼ģ”↵↵

-0.13

lettes

-0.13

 ê¼

-0.13

our

-0.13

POSITIVE LOGITS

 should

0.19

.should

0.18

 future

0.18

 perhaps

0.18

 need

0.17

eday

0.17

 ought

0.17

 McGill

0.17

.TODO

0.17

.todo

0.16

Activations Density 0.018%

programming-related comments that indicate tasks or improvements needed in the code

No Comments

No Known Activations