INDEX

Explanations

phrases that reference examples or instances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

atura

-0.17

WithMany

-0.16

 more

-0.15

ahlen

-0.14

nid

-0.14

plr

-0.14

gers

-0.14

 least

-0.14

aturas

-0.14

ÑĨÑĸÐ¹Ð½Ð°

-0.14

POSITIVE LOGITS

åĮħæĭ¬

0.15

0.14

 ê²ĥëıĦ

0.14

akin

0.14

opot

0.14

Means

0.13

ince

0.13

.us

0.12

#:

0.12

Activations Density 0.060%

phrases that reference examples or instances

No Comments

No Known Activations