INDEX

Explanations

different types of input and output data related to programming and processing elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

_inputs

-0.18

Inputs

-0.17

/is

-0.17

_inp

-0.16

opus

-0.15

abeth

-0.15

Input

-0.15

infeld

-0.15

iana

-0.15

input

-0.15

POSITIVE LOGITS

ted

0.49

ting

0.47

/output

0.43

ters

0.38

-output

0.36

TING

0.33

tings

0.27

MethodManager

0.24

TED

0.23

ten

0.22

Activations Density 0.028%

different types of input and output data related to programming and processing elements

No Comments

No Known Activations