INDEX

Explanations

references to government officials and ministries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

bor

-0.15

á»©a

-0.15

ÏĢÎµÎ¹

-0.14

aran

-0.14

áº¡n

-0.14

endor

-0.14

osta

-0.13

unit

-0.13

acity

-0.13

POSITIVE LOGITS

ial

0.25

IAL

0.18

wide

0.18

aires

0.15

lake

0.15

:min

0.15

erva

0.14

ochond

0.14

ials

0.14

Ð½Ð¾

0.14

Activations Density 0.023%

references to government officials and ministries

No Comments

No Known Activations