INDEX

Explanations

references to large quantities of people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ignet

-0.17

emens

-0.15

olver

-0.15

UGE

-0.14

ependency

-0.14

ube

-0.14

icable

-0.14

ihan

-0.14

ensi

-0.14

 Waters

-0.14

POSITIVE LOGITS

GV

0.15

itter

0.14

sten

0.14

ctal

0.14

osite

0.14

 thousands

0.13

.com

0.13

fold

0.13

_errno

0.13

ITTER

0.13

Activations Density 0.025%

references to large quantities of people or entities

No Comments

No Known Activations