INDEX

Explanations

the repeated use of the word "We."

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

 Fuse

-0.15

trak

-0.15

_LT

-0.15

ITE

-0.15

å¼µ

-0.15

Æ¯á»

-0.14

thon

-0.14

acl

-0.13

ITE

-0.13

wel

-0.13

POSITIVE LOGITS

alth

0.18

 à¸¿

0.15

orsk

0.15

bsite

0.15

umm

0.14

ir

0.14

chy

0.14

à¸¶à¸ģ

0.14

aliz

0.14

ocity

0.13

Activations Density 0.012%

the repeated use of the word "We."

No Comments

No Known Activations