INDEX

Explanations

references to quantities, counts, and statistics related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ensa

-0.16

 lick

-0.15

nyder

-0.15

 elsewhere

-0.15

onnement

-0.15

áº©m

-0.14

áº»

-0.14

å¯¸

-0.14

ÐŁÐļ

-0.13

 wherever

-0.13

POSITIVE LOGITS

per

0.32

 each

0.23

 needed

0.22

 available

0.21

 ÙĦÙĥÙĦ

0.21

needed

0.19

 present

0.19

 má»Ĺi

0.19

Needed

0.18

_per

0.18

Activations Density 0.168%

references to quantities, counts, and statistics related to various subjects

No Comments

No Known Activations