INDEX

Explanations

names of organizations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

indow

-0.15

ranÃŃ

-0.14

 miejsc

-0.14

uning

-0.14

atan

-0.13

ovi

-0.13

hint

-0.13

htub

-0.13

ahas

-0.13

((*

-0.13

POSITIVE LOGITS

oley

0.17

/Foundation

0.17

 Uncategorized

0.15

avar

0.15

 /↵↵

0.15

eka

0.14

.maps

0.14

Usa

0.14

 Logo

0.14

ivirus

0.14

Activations Density 0.083%

names of organizations and institutions

No Comments

No Known Activations