INDEX

Explanations

words associated with fear, confusion, and emotional impact

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

steller

-0.15

inize

-0.14

opsis

-0.14

mÃ¼r

-0.14

imler

-0.14

Sai

-0.14

 Ð±ÑĥÐ´ÑĤÐ¾

-0.14

gere

-0.13

BOSE

-0.13

Animating

-0.13

POSITIVE LOGITS

ingly

0.21

 mnie

0.16

ni

0.14

xAF

0.14

orer

0.14

edo

0.14

HIR

0.14

desk

0.14

 cach

0.14

undo

0.13

Activations Density 0.072%

words associated with fear, confusion, and emotional impact

No Comments

No Known Activations