INDEX

Explanations

words related to specific brands or product names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.29

ichten

-0.21

yb

-0.20

ey

-0.20

ic

-0.20

yar

-0.20

er

-0.20

-0.18

yw

-0.16

trees

-0.16

POSITIVE LOGITS

py

0.28

portunity

0.25

inions

0.23

pi

0.23

pen

0.22

ausal

0.22

edia

0.21

pler

0.21

kins

0.20

engl

0.20

Activations Density 0.030%

words related to specific brands or product names

No Comments

No Known Activations