INDEX

Explanations

references to logging and data structure operations

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

Ð¾Ð²Ð°ÑĢÐ¸

-0.16

]={↵

-0.14

 Armstrong

-0.14

æĪ»

-0.14

Loading

-0.14

.CODE

-0.14

IVING

-0.14

-0.13

loader

-0.13

 ÑģÐºÐ°

-0.13

POSITIVE LOGITS

log

0.56

 logs

0.51

Log

0.47

 Logs

0.44

.log

0.42

log

0.40

-log

0.39

_log

0.39

Log

0.38

Logs

0.38

Activations Density 0.082%

references to logging and data structure operations

No Comments

No Known Activations