INDEX

Explanations

phrases that indicate observation or visualization

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

CHIP

-0.17

iyat

-0.15

adden

-0.15

_ASYNC

-0.14

wil

-0.14

iro

-0.14

è¹

-0.14

enville

-0.14

ellas

-0.14

ãĥŃãĥ¼

-0.14

POSITIVE LOGITS

ools

0.16

0.15

 Millennium

0.15

0.14

ilde

0.14

zej

0.14

INET

0.14

pid

0.14

0.13

Activations Density 0.193%

phrases that indicate observation or visualization

No Comments

No Known Activations