INDEX

Explanations

phrases indicating necessity or urgent calls to action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ouch

-0.16

OrNull

-0.15

iggins

-0.15

 Wikip

-0.15

orn

-0.15

acin

-0.14

 pres

-0.14

orte

-0.13

 Exped

-0.13

esso

-0.13

POSITIVE LOGITS

Î²Î¿Î»

0.15

isks

0.15

yal

0.14

roys

0.14

yles

0.14

 Champagne

0.14

hoe

0.14

oga

0.14

.toCharArray

0.14

Activations Density 0.616%

phrases indicating necessity or urgent calls to action

No Comments

No Known Activations