INDEX

Explanations

words related to cultural entities or institutions, particularly museums

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÅĻev

-0.17

.annot

-0.15

thy

-0.15

thon

-0.14

.hashCode

-0.14

à¹ĥ

-0.14

íķĻê¸°

-0.14

croft

-0.13

den

-0.13

ITHER

-0.13

POSITIVE LOGITS

PathParam

0.16

 addslashes

0.15

gements

0.14

Weekly

0.14

 Separator

0.14

weekly

0.14

istical

0.14

aines

0.14

Äĵ

0.14

 Transparency

0.14

Activations Density 0.010%

words related to cultural entities or institutions, particularly museums

No Comments

No Known Activations