INDEX

Explanations

mentions of unknown or unidentified entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

.scalablytyped

-0.20

uir

-0.15

istr

-0.15

back

-0.14

iste

-0.14

eview

-0.14

rine

-0.14

igate

-0.14

roe

-0.14

 Colon

-0.14

POSITIVE LOGITS

HostException

0.26

/un

0.20

0.19

 unknown

0.18

ingly

0.17

ariat

0.17

etter

0.17

sis

0.16

 assail

0.15

ledge

0.15

Activations Density 0.036%

mentions of unknown or unidentified entities

No Comments

No Known Activations