INDEX

Explanations

function definitions and related operations within programming or code structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

istrovstvÃŃ

-0.18

ldr

-0.17

ieten

-0.15

itez

-0.15

zem

-0.15

åħį

-0.14

icken

-0.14

_GENERIC

-0.14

alen

-0.13

à¹ĳ

-0.13

POSITIVE LOGITS

 const

0.42

const

0.33

)const

0.28

 Const

0.26

	const

0.26

(const

0.26

.const

0.21

Const

0.21

,const

0.20

_const

0.20

Activations Density 0.010%

function definitions and related operations within programming or code structures

No Comments

No Known Activations