INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ê²

-0.18

 Loft

-0.16

amil

-0.15

iram

-0.15

ander

-0.14

izon

-0.14

oggles

-0.14

amedi

-0.14

 expiry

-0.14

expiry

-0.14

POSITIVE LOGITS

Ð¾Ð±Ð°

0.16

obus

0.16

printer

0.15

 TORT

0.15

 guaranteed

0.14

 Slav

0.14

dag

0.14

.sl

0.13

ìļ´

0.13

 Ð¢Ð¸Ð¼

0.13

Activations Density 0.306%

expressions of gratitude and appreciation

No Comments

No Known Activations