INDEX

Explanations

references to steel

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

ameda

-0.16

ellan

-0.16

rait

-0.16

es

-0.15

encer

-0.15

st

-0.15

elli

-0.14

hog

-0.14

 Elaine

-0.13

 Everett

-0.13

POSITIVE LOGITS

ibold

0.17

 olsa

0.16

åħĦ

0.16

urgy

0.15

inox

0.15

ights

0.14

igi

0.14

.SwingConstants

0.14

iÄħ

0.14

sheets

0.14

Activations Density 0.008%

references to steel

No Comments

No Known Activations