INDEX

Explanations

technical terms and concepts related to programming and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

CKET

-0.16

aggio

-0.15

wa

-0.15

Ble

-0.14

StreamWriter

-0.14

abox

-0.14

Wa

-0.14

åİ

-0.14

InputBorder

-0.14

raries

-0.13

POSITIVE LOGITS

 bound

0.29

 Bound

0.27

bound

0.25

Bound

0.24

-bound

0.23

 Binding

0.21

_bound

0.21

row

0.20

 binding

0.20

 bind

0.20

Activations Density 0.039%

technical terms and concepts related to programming and data handling

No Comments

No Known Activations