INDEX

Explanations

phrases indicating physical manipulation or control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ksen

-0.17

ocy

-0.17

irq

-0.15

èı¯

-0.14

SPARENT

-0.13

 vÃ¤l

-0.13

à¥įà¤

-0.13

/memory

-0.13

laÄį

-0.13

creative

-0.13

POSITIVE LOGITS

ÅĻe

0.16

mens

0.15

alar

0.15

/stream

0.15

olid

0.14

Ú¯ÛĮØ±ÛĮ

0.14

Jas

0.14

alin

0.14

.SimpleButton

0.14

eres

0.14

Activations Density 0.030%

phrases indicating physical manipulation or control

No Comments

No Known Activations