INDEX

Explanations

references to educational institutions and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ð¾ÑģÑĮ

-0.17

uil

-0.16

aux

-0.15

 Casual

-0.15

ering

-0.14

 buck

-0.14

Ð°Ð½Ñĸ

-0.14

UIL

-0.14

reau

-0.14

 splitter

-0.14

POSITIVE LOGITS

ardy

0.17

ordo

0.16

ula

0.16

unt

0.15

ndon

0.14

unt

0.14

urgeon

0.14

adele

0.14

à¸£à¸°

0.14

Activations Density 0.217%

references to educational institutions and related terminology

No Comments

No Known Activations