INDEX

Explanations

components related to product specifications and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ORIZED

-0.18

.travel

-0.17

 Ð¿Ð°

-0.14

 clipping

-0.14

.lp

-0.14

 traveled

-0.13

assi

-0.13

ravel

-0.13

athi

-0.13

Axe

-0.13

POSITIVE LOGITS

ernet

0.16

etail

0.15

iele

0.15

ished

0.15

fin

0.14

.std

0.14

iple

0.14

warts

0.13

tin

0.13

die

0.13

Activations Density 0.002%

components related to product specifications and features

No Comments

No Known Activations