INDEX

Explanations

terms related to effort and difficulty

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

ssi

-0.16

Ã´m

-0.16

upert

-0.15

 Likes

-0.15

ESH

-0.15

ÙĪØµ

-0.14

(strtolower

-0.14

essel

-0.14

idar

-0.14

ded

-0.14

POSITIVE LOGITS

 enough

0.27

(er

0.21

 Enough

0.20

à¹Ĩ

0.18

Enough

0.16

ently

0.16

à¤¤à¤®

0.16

wards

0.16

Ø§ÙĨÙĩ

0.15

ely

0.14

Activations Density 0.295%

terms related to effort and difficulty

No Comments

No Known Activations