INDEX

Explanations

factual information and statistics related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

oris

-0.16

pot

-0.15

arrow

-0.15

elsen

-0.15

llen

-0.14

adesh

-0.14

LEM

-0.13

esen

-0.13

liner

-0.13

hil

-0.13

POSITIVE LOGITS

ä»¥ä¸Ĭ

0.26

 ìĿ´ìĥģ

0.22

or

0.21

 trá»Ł

0.18

åıĬåħ¶

0.16

æĪĸèĢħ

0.16

loquent

0.16

 hoáº·c

0.16

 oder

0.15

 minimum

0.15

Activations Density 0.092%

factual information and statistics related to various topics

No Comments

No Known Activations