INDEX

Explanations

references to uniqueness and exceptionalism

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

inee

-0.20

-0.19

nic

-0.16

ä¸¸

-0.15

illac

-0.15

ucci

-0.15

rient

-0.15

Ð¾Ð»Ð¾Ð²

-0.15

-0.14

POSITIVE LOGITS

 Walters

0.16

indle

0.14

ernes

0.14

onom

0.14

 Kidd

0.14

 ìŀ¡

0.14

éĺµ

0.14

ë¦Ħ

0.13

ussen

0.13

azi

0.13

Activations Density 0.069%

references to uniqueness and exceptionalism

No Comments

No Known Activations