INDEX

Explanations

actions involving recognition and participation in activities or events

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

forall

-0.17

 oneself

-0.16

obuf

-0.16

everyone

-0.15

 everybody

-0.15

Ã³w

-0.15

cludes

-0.15

something

-0.15

anes

-0.14

Everybody

-0.14

POSITIVE LOGITS

 some

0.35

some

0.29

 Some

0.27

 algun

0.26

.some

0.24

 einige

0.24

Some

0.24

 none

0.23

 SOME

0.23

 Ð½ÐµÐºÐ¾ÑĤÐ¾ÑĢÑĭÐµ

0.23

Activations Density 0.016%

actions involving recognition and participation in activities or events

No Comments

No Known Activations