INDEX

Explanations

references to community involvement and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Ð¾Ð½Ð¾

-0.14

Ã

-0.14

>.↵↵

-0.13

å®ĥä»¬

-0.13

$MESS

-0.13

utschein

-0.13

/.↵↵

-0.13

hazi

-0.13

iliz

-0.13

 ÙģÙĩ

-0.13

POSITIVE LOGITS

odore

0.23

 another

0.20

etheless

0.19

 meanwhile

0.18

 foregoing

0.18

 other

0.18

bsites

0.17

adays

0.17

 Another

0.16

Another

0.15

Activations Density 0.296%

references to community involvement and support

No Comments

No Known Activations