INDEX

Explanations

references to journal articles and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ø§Ø±Ø§ÙĨ

-0.16

ray

-0.15

áº©n

-0.15

moz

-0.14

fu

-0.14

pants

-0.14

 Pied

-0.14

åŁ·

-0.13

altar

-0.13

 Malk

-0.13

POSITIVE LOGITS

iele

0.16

/themes

0.16

isposable

0.15

-before

0.14

itra

0.14

oved

0.14

/vnd

0.14

spot

0.13

oley

0.13

iÄĻ

0.13

Activations Density 0.005%

references to journal articles and their components

No Comments

No Known Activations