INDEX

Explanations

instances of surprise or unexpected events

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

.scalablytyped

-0.19

ajs

-0.17

une

-0.16

-ci

-0.15

isters

-0.14

stre

-0.14

ICLES

-0.14

serter

-0.14

ishops

-0.14

gie

-0.13

POSITIVE LOGITS

ingly

0.32

ably

0.23

 surprise

0.20

ously

0.18

 Surprise

0.18

 surpr

0.18

IPA

0.16

 surprised

0.16

ylon

0.16

/errors

0.15

Activations Density 0.051%

instances of surprise or unexpected events

No Comments

No Known Activations