INDEX

Explanations

markers related to tasks or issues that need attention in code documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

undler

-0.16

âĢ¦"↵↵

-0.14

zcze

-0.13

æ´¥

-0.13

ãĥ³ãĥĸ

-0.13

Ø°Ø±

-0.13

_COMPILER

-0.13

 ê¼

-0.13

Wa

-0.13

"><!--

-0.13

POSITIVE LOGITS

.should

0.19

 perhaps

0.18

 should

0.18

 proper

0.18

 Should

0.17

.todo

0.17

 McGill

0.16

 eventually

0.16

 ought

0.16

proper

0.16

Activations Density 0.023%

markers related to tasks or issues that need attention in code documentation

No Comments

No Known Activations