INDEX

Explanations

phrases indicating limitations or the absence of necessary qualities or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uchi

-0.16

berman

-0.16

dden

-0.15

tep

-0.15

ÑĥÑĢÐ¸

-0.14

 subsidi

-0.14

()(

-0.14

elles

-0.14

eah

-0.13

æŃ©

-0.13

POSITIVE LOGITS

 means

0.34

 resources

0.33

 inclination

0.28

 funds

0.27

means

0.27

 Means

0.25

 sufficient

0.25

 capacity

0.25

 necessary

0.25

 tools

0.25

Activations Density 0.159%

phrases indicating limitations or the absence of necessary qualities or resources

No Comments

No Known Activations