INDEX

Explanations

terms related to significant advancements or successes

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

ØªÙĪÙĨ

-0.18

æŀ

-0.15

loat

-0.14

å¹¼

-0.14

lack

-0.14

à¸Ńà¹Ģà¸£

-0.14

PRESS

-0.14

hang

-0.13

RF

-0.13

getc

-0.13

POSITIVE LOGITS

ipse

0.18

_simps

0.15

uppe

0.15

idth

0.15

 into

0.15

ÑģÑĸÐ¼

0.14

ÑĥÐ»Ñİ

0.14

_into

0.14

Into

0.14

ACHE

0.14

Activations Density 0.030%

terms related to significant advancements or successes

No Comments

No Known Activations