INDEX

Explanations

references to system states or error codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

echa

-0.16

Î³Î·

-0.16

tings

-0.15

olated

-0.15

eled

-0.15

à¹Ģà¸Ĺ

-0.15

@qq

-0.14

edom

-0.14

eut

-0.14

 èĮ

-0.14

POSITIVE LOGITS

uster

0.15

 Mayor

0.14

 Ð¿ÑĢÐ¾Ð·

0.14

&a

0.14

 Roch

0.14

hm

0.14

 unitOfWork

0.14

atura

0.14

asc

0.14

ÐºÑĢÐ°

0.14

Activations Density 0.039%

references to system states or error codes

No Comments

No Known Activations