INDEX

Explanations

strong descriptive adjectives and effective communication elements

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

ema

-0.19

inger

-0.15

eam

-0.15

chner

-0.15

ussen

-0.15

Ã¥l

-0.14

yll

-0.14

Î¹ÎºÎ¿

-0.14

Ã¹i

-0.14

uss

-0.14

POSITIVE LOGITS

 rise

0.24

äºĪ

0.21

 preference

0.20

 permission

0.19

aways

0.17

 Give

0.17

 directions

0.17

away

0.16

 Directions

0.16

 impression

0.16

Activations Density 0.122%

strong descriptive adjectives and effective communication elements

No Comments

No Known Activations