INDEX

Explanations

references to engagement and exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ali

-0.17

izont

-0.16

ÑĭÑģ

-0.15

Å¾ÃŃ

-0.15

nz

-0.15

mts

-0.14

BED

-0.14

\`

-0.14

orny

-0.14

SearchTree

-0.14

POSITIVE LOGITS

 exception

0.25

no

0.23

 exceptions

0.22

exceptions

0.19

ä¾ĭ

0.19

 Exceptions

0.19

ä¹Łä¸į

0.17

 same

0.17

_exception

0.16

exception

0.16

Activations Density 0.051%

references to engagement and exceptions

No Comments

No Known Activations