INDEX

Explanations

the presence of the word "ado," indicating a focus on excitable or action-oriented topics

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

erb

-0.15

nal

-0.15

aggio

-0.14

figcaption

-0.14

ville

-0.14

ker

-0.14

oki

-0.14

 sovere

-0.13

kening

-0.13

ypy

-0.13

POSITIVE LOGITS

 Gross

0.17

oons

0.16

 McCart

0.15

.sd

0.14

abra

0.14

Cri

0.14

 Cord

0.13

 cups

0.13

gross

0.13

 gross

0.13

Activations Density 0.016%

the presence of the word "ado," indicating a focus on excitable or action-oriented topics

No Comments

No Known Activations