INDEX

Explanations

references to assistance or help in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

InnerText

-0.17

TestCategory

-0.14

trap

-0.14

Ð¾ÑģÐ¿

-0.14

rees

-0.13

arda

-0.13

 Ù¾Ø°ÛĮØ±

-0.13

ivan

-0.13

AGR

-0.13

.snapshot

-0.13

POSITIVE LOGITS

dem

0.29

arm

0.29

 familiar

0.26

 orient

0.23

 walks

0.23

 walk

0.23

 guide

0.21

Fam

0.21

 point

0.21

 answer

0.20

Activations Density 0.107%

references to assistance or help in various contexts

No Comments

No Known Activations