INDEX

Explanations

references to logging frameworks in code

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

tsky

-0.17

yleft

-0.14

raphics

-0.14

zimmer

-0.14

_scores

-0.14

tega

-0.14

secutive

-0.14

iro

-0.13

rap

-0.13

 slit

-0.13

POSITIVE LOGITS

 rolling

0.25

 Rolling

0.24

rolling

0.23

Skeleton

0.22

 Pattern

0.21

Layout

0.19

 Layout

0.19

.layout

0.18

layout

0.18

enders

0.18

Activations Density 0.003%

references to logging frameworks in code

No Comments

No Known Activations