INDEX

Explanations

references to specific geographical locations and governmental structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ã©gor

-0.16

iffe

-0.15

 meisten

-0.14

 fisse

-0.14

dÃ¼

-0.14

arie

-0.14

emmel

-0.14

Î³ÎµÎ¹

-0.14

kest

-0.14

nave

-0.14

POSITIVE LOGITS

isses

0.18

es

0.18

 Gins

0.17

usses

0.17

asters

0.17

ikes

0.17

ains

0.16

ieres

0.16

}s

0.16

systems

0.16

Activations Density 0.019%

references to specific geographical locations and governmental structures

No Comments

No Known Activations