INDEX

Explanations

names and terms related to organizations, businesses, and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Ã¼st

-0.14

 Coch

-0.14

ald

-0.14

yn

-0.14

Dra

-0.14

led

-0.13

 Hayes

-0.13

 dreaming

-0.13

ing

-0.13

ydro

-0.13

POSITIVE LOGITS

akin

0.19

 shalt

0.15

ÐºÑĤÐ¸

0.14

é½

0.14

iele

0.14

hung

0.14

arella

0.14

ewise

0.14

enzhen

0.14

imore

0.13

Activations Density 0.228%

names and terms related to organizations, businesses, and their activities

No Comments

No Known Activations