INDEX

Explanations

phrases indicating confirmation or assurance of previous statements

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

this

-0.18

 this

-0.18

éĤ£æł·

-0.15

zer

-0.15

è¿Ļä¸Ģ

-0.15

ts

-0.15

.ts

-0.15

thus

-0.15

 pilot

-0.14

POSITIVE LOGITS

 happen

0.17

 happening

0.17

 happens

0.17

ìłĢ

0.15

WithTitle

0.15

íĮĶ

0.15

 happened

0.15

ãĥ¼ãĥĲ

0.15

Rick

0.14

Them

0.14

Activations Density 0.275%

phrases indicating confirmation or assurance of previous statements

No Comments

No Known Activations