INDEX

Explanations

phrases emphasizing an important concept or element, often referred to as "the thing."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

aille

-0.16

iman

-0.16

allen

-0.15

usz

-0.15

ansom

-0.15

odial

-0.15

igli

-0.14

adin

-0.14

vu

-0.14

versible

-0.14

POSITIVE LOGITS

(s

0.15

yard

0.14

hic

0.14

-yard

0.14

amo

0.14

azio

0.13

ometrics

0.13

ICC

0.13

elpers

0.13

ummy

0.13

Activations Density 0.051%

phrases emphasizing an important concept or element, often referred to as "the thing."

No Comments

No Known Activations