INDEX

Explanations

terms related to archives and organizational structures

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

sk

-0.21

se

-0.18

st

-0.18

-0.17

la

-0.17

sh

-0.15

ils

-0.15

-sk

-0.15

osh

-0.15

POSITIVE LOGITS

Ð½ÑĭÐ¹

0.59

Ð½ÑĭÐµ

0.57

Ð½Ð¾Ðµ

0.56

Ð½Ð°Ñı

0.55

Ð½Ð¾Ð¹

0.54

Ð½ÑĭÑħ

0.52

Ð½ÑĥÑİ

0.51

Ð½ÑĭÐ¼

0.51

Ð½Ð¾Ð³Ð¾

0.50

Ð½ÑĭÐ¼Ð¸

0.47

Activations Density 0.026%

terms related to archives and organizational structures

No Comments

No Known Activations