INDEX

Explanations

phrases related to misconceptions and myths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

steen

-0.16

 Cant

-0.15

ViewState

-0.15

Esc

-0.15

echa

-0.15

áº¡nh

-0.15

iture

-0.15

avra

-0.14

itti

-0.14

ellow

-0.14

POSITIVE LOGITS

fare

0.16

AllWindows

0.14

ymph

0.14

Ø§ÙģÛĮ

0.14

IDEOS

0.14

opal

0.14

ION

0.14

ãĥªãĥ³

0.13

zin

0.13

 Spiritual

0.13

Activations Density 0.215%

phrases related to misconceptions and myths

No Comments

No Known Activations