INDEX

Explanations

phrases that question the relevance of certain topics or emphasize oversaturation in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

pun

-0.17

asher

-0.17

.openg

-0.14

Ð¼Ð¾ÑĢ

-0.14

Vet

-0.14

è½®

-0.14

alon

-0.14

rough

-0.14

ighthouse

-0.14

ge

-0.14

POSITIVE LOGITS

 unfortunately

0.18

 often

0.17

 íĿĶ

0.15

å¿Ļ

0.15

Unfortunately

0.15

often

0.15

venta

0.15

 sadly

0.14

too

0.14

OLEAN

0.14

Activations Density 0.408%

phrases that question the relevance of certain topics or emphasize oversaturation in discussions

No Comments

No Known Activations