INDEX

Explanations

code related to database operations

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

aar

-0.16

\↵

-0.14

 \č↵

-0.14

Ã¶g

-0.13

rax

-0.13

aab

-0.13

 createState

-0.13

ayet

-0.13

nop

-0.13

 Pike

-0.12

POSITIVE LOGITS

 your

0.16

erland

0.15

 Your

0.15

 [âĢ¦

0.14

[=

0.14

Your

0.14

 Magical

0.13

unce

0.13

.kotlin

0.13

ires

0.13

Activations Density 0.064%

code related to database operations

No Comments

No Known Activations