INDEX

Explanations

situations where distinctions or differences between entities are made

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

_INTERFACE

-0.15

maxLength

-0.15

angan

-0.14

.rs

-0.14

alla

-0.14

_bridge

-0.14

.qq

-0.14

pie

-0.14

iew

-0.13

èµ¶

-0.13

POSITIVE LOGITS

 distinction

0.38

 differentiation

0.33

 distinctions

0.32

 differentiate

0.30

 distinguish

0.28

istingu

0.28

 confusion

0.27

istinguish

0.27

 distinguishing

0.27

 discrimination

0.27

Activations Density 0.146%

situations where distinctions or differences between entities are made

No Comments

No Known Activations