INDEX

Explanations

sequences related to entertainment or media content, particularly identifying related file types or structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

anka

-0.16

orsk

-0.15

Įĵ

-0.15

enk

-0.14

ovsky

-0.14

uide

-0.14

aque

-0.14

esseract

-0.14

åı¸

-0.14

Ã¨ve

-0.14

POSITIVE LOGITS

ARGIN

0.15

oo

0.15

ward

0.15

ogg

0.14

imoto

0.14

 éĸ

0.14

ÑħÐ¾Ð²

0.14

ERV

0.14

0.13

.epam

0.13

Activations Density 0.019%

sequences related to entertainment or media content, particularly identifying related file types or structures

No Comments

No Known Activations