INDEX

Explanations

unusual or non-standard characters, symbols, and formatting elements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð±ÑĥÐ´

-0.14

loquent

-0.14

liÄį

-0.14

hsi

-0.13

leton

-0.13

Î¹Î»

-0.13

okia

-0.13

chers

-0.13

annya

-0.13

oli

-0.13

POSITIVE LOGITS

 even

0.35

even

0.30

 Even

0.29

 EVEN

0.28

Even

0.28

 Ð´Ð°Ð¶Ðµ

0.24

 sogar

0.23

çĶļèĩ³

0.23

_even

0.22

-even

0.21

Activations Density 0.008%

unusual or non-standard characters, symbols, and formatting elements within the text

No Comments

No Known Activations