INDEX

Explanations

references to programming functions and system events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ESSAGE

-0.17

ira

-0.16

ima

-0.16

let

-0.16

ft

-0.16

led

-0.16

izer

-0.15

Torrent

-0.15

BJECT

-0.15

©

-0.15

POSITIVE LOGITS

0.33

/OR

0.24

ING

0.23

ER

0.20

tember

0.19

IS

0.19

_EDEFAULT

0.18

LY

0.18

swers

0.18

’S

0.17

Activations Density 0.375%

references to programming functions and system events

No Comments

No Known Activations