INDEX

Explanations

mentions of locations or addresses, particularly within the USA and Canada

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

Ã¼ss

-0.18

led

-0.16

kop

-0.16

Transfer

-0.15

ammers

-0.15

 Transfer

-0.15

èĭ

-0.15

Wig

-0.14

transfer

-0.14

uario

-0.14

POSITIVE LOGITS

 refl

0.17

ITCH

0.15

 ØªØŃØµ

0.14

rael

0.14

(Handle

0.14

/commons

0.14

 Marriott

0.14

.asInstanceOf

0.14

itch

0.13

razier

0.13

Activations Density 0.067%

mentions of locations or addresses, particularly within the USA and Canada

No Comments

No Known Activations