INDEX

Explanations

comments or TODOs 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 @ 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

ÑĢÑĮ

-0.15

.nlm

-0.15

Ð¾ÐºÑĢÐµÐ¼Ð°

-0.14

opyright

-0.14

reamble

-0.14

.Disclaimer

-0.13

uala

-0.13

undler

-0.13

.ReadString

-0.13

utility

-0.13

POSITIVE LOGITS

 figure

0.21

 implement

0.20

 finish

0.20

 proper

0.19

fix

0.19

 perhaps

0.19

proper

0.18

 properly

0.18

 FIXME

0.17

 better

0.17

Activations Density 0.033%

comments or TODOs in code

No Comments

No Known Activations