INDEX

Explanations

phrases that indicate causality or reason

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ne

-0.19

²

-0.17

RECT

-0.17

so

-0.16

uch

-0.16

ka

-0.16

red

-0.15

ach

-0.14

 GÃ¼n

-0.14

tr

-0.14

POSITIVE LOGITS

 diligence

0.20

ighter

0.16

ogh

0.15

Ð¾Ð³Ð¾Ð´

0.15

Ã±as

0.15

gfx

0.15

CLS

0.15

 dilig

0.15

erus

0.15

erdale

0.15

Activations Density 0.020%

phrases that indicate causality or reason

No Comments

No Known Activations