INDEX

Explanations

technical terms and concepts related to data structures and programming functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

adro

-0.16

-0.14

chai

-0.14

 Remix

-0.14

.pat

-0.14

ÑĢÐ°ÑħÐ¾Ð²

-0.13

Ð»ÑıÐ½

-0.13

Ag

-0.13

ety

-0.13

rer

-0.13

POSITIVE LOGITS

0.38

 =↵

0.22

 =↵↵

0.20

=(

0.18

&=

0.16

 =č↵

0.15

0.14

uru

0.14

 Altern

0.14

ilden

0.14

Activations Density 0.079%

technical terms and concepts related to data structures and programming functions

No Comments

No Known Activations