INDEX

Explanations

instances of the word "the" and other articles, indicating a focus on specific details or elements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Hayward

-0.15

ousse

-0.15

-regexp

-0.14

-mf

-0.14

URN

-0.14

lav

-0.14

bery

-0.13

azel

-0.13

.mu

-0.13

POSITIVE LOGITS

/or

0.16

ijd

0.16

anlÄ±

0.14

ovich

0.14

.biz

0.14

une

0.14

èį·

0.13

inct

0.13

opia

0.13

andle

0.13

Activations Density 0.219%

instances of the word "the" and other articles, indicating a focus on specific details or elements within the text

No Comments

No Known Activations