INDEX

Explanations

references to logos and branding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oga

-0.18

zk

-0.17

erman

-0.17

falls

-0.15

ingle

-0.15

ken

-0.15

pour

-0.15

æĻ¯

-0.15

hab

-0.15

halb

-0.14

POSITIVE LOGITS

/logo

0.21

osate

0.18

/name

0.17

/sign

0.16

regunta

0.15

 design

0.15

 alignSelf

0.15

strup

0.14

nection

0.14

 premises

0.14

Activations Density 0.020%

references to logos and branding elements

No Comments

No Known Activations