INDEX

Explanations

names of notable individuals or entities related to a specific field

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

ahat

-0.15

InputGroup

-0.15

kov

-0.14

Kit

-0.14

.executeQuery

-0.14

vard

-0.14

ises

-0.14

.uml

-0.14

getter

-0.13

missive

-0.13

POSITIVE LOGITS

ottie

0.16

acman

0.15

emma

0.15

gii

0.15

iland

0.15

 UIBar

0.14

oku

0.14

seg

0.14

ophon

0.14

loh

0.14

Activations Density 0.523%

names of notable individuals or entities related to a specific field

No Comments

No Known Activations