INDEX

Explanations

expressions indicating superiority or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ungan

-0.15

iddi

-0.15

ittest

-0.15

llib

-0.15

dden

-0.15

tees

-0.15

ÙĪØ¯ÛĮ

-0.14

ssize

-0.14

writer

-0.14

 fewer

-0.14

POSITIVE LOGITS

seller

0.23

owing

0.23

-selling

0.21

-known

0.20

ow

0.19

-case

0.18

wick

0.18

jamin

0.17

ØªØ²

0.17

AGMA

0.16

Activations Density 0.057%

expressions indicating superiority or quality

No Comments

No Known Activations