INDEX

Explanations

verbs associated with actions, particularly in the context of change or transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.16

Ð¸ÑĪ

-0.16

antz

-0.15

ardless

-0.14

ertest

-0.14

 Richardson

-0.14

ello

-0.14

ishments

-0.14

uen

-0.14

isted

-0.14

POSITIVE LOGITS

ÃŃa

0.31

Ã¡

0.28

Ãł

0.28

ia

0.26

Ã¡n

0.23

ait

0.23

ont

0.20

anno

0.19

mos

0.18

emos

0.18

Activations Density 0.009%

verbs associated with actions, particularly in the context of change or transformation

No Comments

No Known Activations