INDEX

Explanations

numerical data related to research articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

iente

-0.18

viso

-0.15

ientes

-0.14

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.14

ato

-0.14

ivo

-0.14

BUR

-0.14

Î´Î±

-0.14

tero

-0.14

cio

-0.13

POSITIVE LOGITS

jee

0.16

ff

0.16

tha

0.16

 Silver

0.15

Silver

0.15

jen

0.14

lius

0.14

LP

0.14

yne

0.13

Activations Density 0.039%

numerical data related to research articles

No Comments

No Known Activations