INDEX

Explanations

information about significant events or attributes related to personal or professional background

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

isini

-0.19

-0.18

Ð¾Ð²ÐµÑĢ

-0.17

erah

-0.16

_OM

-0.16

à¤¦à¤°

-0.15

cente

-0.15

utas

-0.14

.semantic

-0.14

.dtd

-0.14

POSITIVE LOGITS

 vanity

0.17

 solid

0.14

lin

0.14

imoto

0.14

ovich

0.14

 solidarity

0.14

ahr

0.14

 Secondly

0.14

andid

0.14

 Them

0.13

Activations Density 0.214%

information about significant events or attributes related to personal or professional background

No Comments

No Known Activations