INDEX

Explanations

phrases that indicate rankings or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.updateDynamic

-0.16

Ã²ng

-0.15

ajas

-0.15

unami

-0.14

mobx

-0.14

ulan

-0.14

udad

-0.14

bes

-0.13

>Contact

-0.13

åħĥ

-0.13

POSITIVE LOGITS

kara

0.17

 Leather

0.17

assi

0.15

:async

0.15

quate

0.14

gew

0.14

abeth

0.14

 autob

0.13

 Zheng

0.13

Activations Density 0.009%

phrases that indicate rankings or lists

No Comments

No Known Activations