INDEX

Explanations

references to the word "who."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

bian

-0.14

uisse

-0.14

uet

-0.14

QUIRES

-0.14

idor

-0.14

gor

-0.14

orial

-0.14

uhan

-0.13

boa

-0.13

.TryParse

-0.13

POSITIVE LOGITS

 else

0.45

 exactly

0.34

 ELSE

0.28

 Else

0.28

else

0.27

/how

0.26

 among

0.25

_else

0.25

 amongst

0.24

	else

0.24

Activations Density 0.028%

references to the word "who."

No Comments

No Known Activations