INDEX

Explanations

references to relationships and connections among individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

OP

-0.15

aque

-0.15

KeyValuePair

-0.15

ulares

-0.14

atas

-0.13

ound

-0.13

_execute

-0.13

utely

-0.13

 ÑĩÐµÑģÑĤÑĮ

-0.13

ÑĤÐ¾Ð¼

-0.13

POSITIVE LOGITS

 others

0.29

 alike

0.25

 similar

0.25

 other

0.23

others

0.23

åħ¶ä»ĸ

0.20

similar

0.19

 simil

0.18

 podob

0.18

 anderen

0.18

Activations Density 0.126%

references to relationships and connections among individuals or groups

No Comments

No Known Activations