INDEX

Explanations

references to social and political dynamics, particularly regarding power structures and inequalities

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

istrovstvÃŃ

-0.17

å³

-0.15

odu

-0.14

 transient

-0.14

encias

-0.14

.Done

-0.14

 Hipp

-0.14

ledge

-0.14

Ã¡ly

-0.14

Ø§Ø°Ø§

-0.13

POSITIVE LOGITS

gid

0.15

ya

0.15

 Griffin

0.15

/tos

0.14

ablish

0.14

oufl

0.14

afi

0.14

igner

0.14

æľį

0.14

fter

0.13

Activations Density 0.332%

references to social and political dynamics, particularly regarding power structures and inequalities

No Comments

No Known Activations