INDEX

Explanations

references to brand names and food-related entities

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

Äĥ

-0.15

 Morrow

-0.14

 panc

-0.14

AILABLE

-0.14

ÌĨ

-0.13

IMARY

-0.13

iego

-0.13

 Ahmet

-0.13

 avid

-0.13

ingt

-0.13

POSITIVE LOGITS

eldorf

0.15

.live

0.14

dateFormat

0.14

.Rec

0.14

uchar

0.14

Ð»Ð¸ÐºÐ°

0.14

 ÙĩÛĮ

0.14

æĭĶ

0.14

 Ð½ÑĸÐ¶

0.14

finder

0.14

Activations Density 0.447%

references to brand names and food-related entities

No Comments

No Known Activations