INDEX

Explanations

phrases indicating purpose or goals in a context

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

ampie

-0.16

anny

-0.15

ETY

-0.15

 íĹ

-0.15

ÑģÑĤÐ°Ð²

-0.14

sak

-0.14

gate

-0.14

annie

-0.14

LOB

-0.14

uario

-0.14

POSITIVE LOGITS

æ³³

0.17

ellas

0.16

0.15

cro

0.15

 Patton

0.15

 Graham

0.14

 finder

0.14

ÏĮÎ³

0.14

eg

0.14

 deployed

0.14

Activations Density 0.025%

phrases indicating purpose or goals in a context

No Comments

No Known Activations