INDEX

Explanations

events and significant occurrences in history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

anki

-0.16

ccb

-0.15

 distract

-0.15

ocket

-0.14

cdecl

-0.14

pek

-0.14

ieu

-0.14

aves

-0.14

incerely

-0.13

unto

-0.13

POSITIVE LOGITS

hua

0.18

 Richt

0.15

 Sticky

0.15

XHR

0.15

0.14

çº

0.14

 birth

0.14

_stylesheet

0.14

Capability

0.14

sticky

0.14

Activations Density 0.042%

events and significant occurrences in history

No Comments

No Known Activations