INDEX

Explanations

phrases indicating assumption or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ookies

-0.15

ÐµÐ»Ð°

-0.15

jal

-0.15

 jenter

-0.14

Ĩ

-0.14

ookie

-0.14

insk

-0.14

ths

-0.13

TextChanged

-0.13

tera

-0.13

POSITIVE LOGITS

avra

0.15

rove

0.15

.arr

0.15

ahren

0.14

CommandEvent

0.14

 Bund

0.14

 newSize

0.14

neh

0.13

olson

0.13

rase

0.13

Activations Density 0.064%

phrases indicating assumption or speculation

No Comments

No Known Activations