INDEX

Explanations

references to US Presidents and significant political events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

eba

-0.14

figcaption

-0.13

aida

-0.13

pedia

-0.13

_RAD

-0.13

 deser

-0.13

Injector

-0.13

fty

-0.13

zens

-0.13

tle

-0.13

POSITIVE LOGITS

 GOODMAN

0.16

ocache

0.15

 Enumerator

0.15

clave

0.15

usty

0.14

ãĥ¼ãĤ¹ãĥĪ

0.14

elig

0.14

rix

0.14

stocks

0.14

ued

0.13

Activations Density 0.118%

references to US Presidents and significant political events

No Comments

No Known Activations