INDEX

Explanations

mentions of the word "one."

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

addy

-0.15

Å©i

-0.15

ersion

-0.15

ifo

-0.15

ottes

-0.14

erdem

-0.14

ase

-0.14

orient

-0.14

searchModel

-0.14

imson

-0.13

POSITIVE LOGITS

of

0.19

cribe

0.16

etwork

0.15

eyi

0.14

etik

0.14

ynos

0.13

ogany

0.13

iw

0.13

amat

0.13

ehen

0.13

Activations Density 0.040%

mentions of the word "one."

No Comments

No Known Activations