INDEX

Explanations

words and phrases related to negative experiences or criticisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ActionBar

-0.17

å¥ī

-0.16

Msp

-0.16

adelphia

-0.15

ÐµÐ·

-0.14

ä¸įäºĨ

-0.14

.stride

-0.14

 ÙĨÙĪÙģ

-0.14

rowable

-0.14

LETTE

-0.14

POSITIVE LOGITS

uzzi

0.15

ulu

0.15

alt

0.15

ici

0.15

alk

0.15

etri

0.15

inch

0.14

asco

0.14

 Reform

0.14

 Carlo

0.14

Activations Density 0.659%

words and phrases related to negative experiences or criticisms

No Comments

No Known Activations