INDEX

Explanations

nested parentheses and groupings in code-like structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Leban

-0.16

 Wick

-0.16

mente

-0.16

ÐĲÑĢÑħÑĸÐ²Ð¾Ð²Ð°Ð½Ð¾

-0.15

seau

-0.15

ÑĳÑĢ

-0.15

uilder

-0.15

ledo

-0.14

ajes

-0.14

Ð½Ð¸ÑĨÐ°

-0.14

POSITIVE LOGITS

eldon

0.17

åį

0.16

0.14

Ð±ÑĢÐ°

0.14

aker

0.14

elta

0.13

ary

0.13

zv

0.13

/vendors

0.12

 Ä°z

0.12

Activations Density 0.060%

nested parentheses and groupings in code-like structures

No Comments

No Known Activations