INDEX

Explanations

elements in programming or coding syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.15

amik

-0.15

:eq

-0.14

uish

-0.14

umpt

-0.14

-dir

-0.14

CanBe

-0.13

elter

-0.13

è¶Ĭ

-0.13

mur

-0.13

POSITIVE LOGITS

sed

0.27

Sed

0.23

sed

0.21

 replace

0.20

 substitute

0.19

 substitution

0.18

 sediment

0.18

 Replace

0.17

SED

0.17

æĽ¿

0.17

Activations Density 0.006%

elements in programming or coding syntax

No Comments

No Known Activations