INDEX

Explanations

references to different classifications or groupings within documents

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

atten

-0.15

ixel

-0.15

iben

-0.15

icina

-0.14

 submitting

-0.14

 submit

-0.14

colo

-0.14

 Lands

-0.14

 Underground

-0.14

.study

-0.13

POSITIVE LOGITS

åĽ

0.18

uing

0.16

 Rouge

0.15

zhou

0.14

ots

0.14

ule

0.14

Rew

0.14

 ÑĢÐ°ÑģÑħÐ¾Ð´

0.14

0.13

 Blanch

0.13

Activations Density 0.011%

references to different classifications or groupings within documents

No Comments

No Known Activations