INDEX

Explanations

rhetorical questions and expressions of curiosity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĤ¤ãĥĦ

-0.16

eyn

-0.16

.contentSize

-0.14

ey

-0.14

felt

-0.14

lld

-0.14

.createClass

-0.14

.Îĳ

-0.14

wie

-0.13

aidu

-0.13

POSITIVE LOGITS

Ð½ÑıÐ²

0.15

amo

0.15

licken

0.14

ichten

0.14

cheon

0.14

AppBundle

0.14

 Berm

0.14

ellan

0.14

 ELSE

0.13

 Observation

0.13

Activations Density 0.019%

rhetorical questions and expressions of curiosity

No Comments

No Known Activations