INDEX

Explanations

logging and assertion-related statements 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÑħÐ¾Ð²

-0.17

aches

-0.17

classnames

-0.16

ÙĦØ§Øª

-0.15

 Abrams

-0.15

isk

-0.14

 Liberties

-0.14

RTC

-0.13

aban

-0.13

amin

-0.13

POSITIVE LOGITS

incy

0.16

 conf

0.15

olle

0.15

illet

0.15

zig

0.15

ÏįÏĢ

0.15

olan

0.15

Ã±ana

0.14

imuth

0.14

olist

0.14

Activations Density 0.326%

logging and assertion-related statements in code

No Comments

No Known Activations