INDEX

Explanations

instances of comparison and contradiction in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Char

-0.16

-0.15

izard

-0.14

ava

-0.14

.eth

-0.14

.Execute

-0.14

 primal

-0.13

AVA

-0.13

vir

-0.13

POSITIVE LOGITS

istrat

0.16

'gc

0.15

lander

0.15

udoku

0.15

 addCriterion

0.14

-tm

0.14

AndPassword

0.14

áºŃu

0.14

ventas

0.14

Kit

0.14

Activations Density 0.615%

instances of comparison and contradiction in various contexts

No Comments

No Known Activations