INDEX

Explanations

references to comparisons and relationships between different entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

è©

-0.15

.gg

-0.13

GetProperty

-0.13

resenter

-0.13

Ð¸Ð½Ð¾Ðº

-0.13

æķ¬

-0.13

afen

-0.13

LETTE

-0.13

ambiguous

-0.12

 correlates

-0.12

POSITIVE LOGITS

 indication

0.50

 indicates

0.50

 indicate

0.48

 indicating

0.45

 suggests

0.43

 Indicates

0.42

 indications

0.41

 suggest

0.41

suggest

0.39

indic

0.39

Activations Density 0.468%

references to comparisons and relationships between different entities or concepts

No Comments

No Known Activations