INDEX

Explanations

numeric codes or identifiers, particularly those formatted with specific patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ÑĥÐ´Ð°

-0.17

 Shutterstock

-0.16

rogen

-0.14

ÑĤÑİ

-0.14

icht

-0.14

à¸£à¸ĵ

-0.13

 Anything

-0.13

isko

-0.13

ask

-0.13

Anything

-0.13

POSITIVE LOGITS

Kaf

0.18

elop

0.15

oriously

0.15

POSITE

0.14

arth

0.14

vore

0.14

igham

0.14

isol

0.14

ifik

0.14

cape

0.14

Activations Density 0.014%

numeric codes or identifiers, particularly those formatted with specific patterns

No Comments

No Known Activations