INDEX

Explanations

references to fees and charges related to services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

erson

-0.17

zo

-0.16

Ale

-0.15

oto

-0.14

 Casting

-0.14

Ned

-0.14

 gains

-0.13

iage

-0.13

oulder

-0.13

nech

-0.13

POSITIVE LOGITS

yonel

0.16

mts

0.16

.ManyToMany

0.15

ozÃŃ

0.15

iman

0.15

nost

0.14

eres

0.14

ETCH

0.14

STA

0.13

imen

0.13

Activations Density 0.036%

references to fees and charges related to services or products

No Comments

No Known Activations