INDEX

Explanations

mentions of the word "change."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

isse

-0.17

 differential

-0.15

ouro

-0.15

 remotely

-0.15

 Cutting

-0.15

arch

-0.14

mith

-0.14

uche

-0.14

 magn

-0.14

chet

-0.14

POSITIVE LOGITS

acente

0.19

YPRE

0.17

 ÄĮer

0.17

ofday

0.16

icode

0.15

iates

0.15

DisplayStyle

0.14

veis

0.14

VERS

0.14

combe

0.14

Activations Density 0.030%

mentions of the word "change."

No Comments

No Known Activations