INDEX

Explanations

comments 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

.p

-0.14

åº¦

-0.14

uch

-0.14

.asp

-0.13

ï»¿

-0.13

umble

-0.13

catid

-0.13

-Ð·Ð°

-0.13

 erst

-0.13

Rib

-0.13

POSITIVE LOGITS

TODO

0.20

 TODO

0.20

0.19

EDIUM

0.18

 eslint

0.18

noinspection

0.17

sweet

0.16

 ...↵↵↵↵

0.16

sink

0.15

 endregion

0.15

Activations Density 0.101%

comments in code

No Comments

No Known Activations