INDEX

Explanations

phrases that express connection or functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

anes

-0.16

 RoundedRectangle

-0.15

åĨµ

-0.15

oblin

-0.15

alone

-0.14

ares

-0.14

du

-0.14

 Winn

-0.14

anas

-0.14

ãĥ©ãĤ¤ãĥĪ

-0.14

POSITIVE LOGITS

etler

0.16

uish

0.15

unes

0.14

bate

0.14

kra

0.14

rek

0.14

reator

0.13

rej

0.13

fet

0.13

preter

0.13

Activations Density 0.077%

phrases that express connection or functionality

No Comments

No Known Activations