INDEX

Explanations

references to fundamental or essential information

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

ynes

-0.18

esi

-0.17

essel

-0.17

eshire

-0.16

hos

-0.15

 specific

-0.15

 Holly

-0.15

 è§

-0.14

/w

-0.13

aklÄ±

-0.13

POSITIVE LOGITS

/basic

0.28

/simple

0.22

mente

0.22

âĢĮØªØ±ÛĮÙĨ

0.21

DBObject

0.20

xes

0.20

/original

0.18

NameValuePair

0.17

ially

0.17

-basic

0.17

Activations Density 0.020%

references to fundamental or essential information

No Comments

No Known Activations