INDEX

Explanations

phrases indicating time-related events and regularly occurring actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

esk

-0.16

.bundle

-0.15

opal

-0.15

uo

-0.14

 Uncomment

-0.14

hv

-0.14

borough

-0.14

-0.13

ofi

-0.13

 aload

-0.13

POSITIVE LOGITS

 permanent

0.67

 permanently

0.60

 Permanent

0.56

permanent

0.56

Permanent

0.56

 perman

0.55

æ°¸ä¹ħ

0.50

 forever

0.37

 ongoing

0.37

 Ð¿Ð¾ÑģÑĤÐ¾ÑıÐ½

0.35

Activations Density 0.352%

phrases indicating time-related events and regularly occurring actions

No Comments

No Known Activations