INDEX

Explanations

references to hospitals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

enser

-0.14

Ã³ria

-0.13

apore

-0.13

æĺ¯åľ¨

-0.13

ylinder

-0.13

 å¹

-0.13

 NotImplementedError

-0.13

oria

-0.13

Bid

-0.13

 Royale

-0.13

POSITIVE LOGITS

inson

0.15

à¥įà¤¯à¤¤

0.15

gett

0.15

ESSAGES

0.14

stell

0.14

ufe

0.14

lava

0.14

peÄį

0.14

ocs

0.14

opleft

0.14

Activations Density 0.013%

references to hospitals

No Comments

No Known Activations