INDEX

Explanations

names and terms related to authors and their works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ustr

-0.15

AYER

-0.14

AVIS

-0.14

beck

-0.14

imum

-0.14

teri

-0.13

bled

-0.13

ERY

-0.13

nob

-0.13

blo

-0.13

POSITIVE LOGITS

0.16

Ã±ana

0.16

ÑĸÐ¹ÑģÑĮÐºÐ¾ÑĹ

0.14

Ã¡o

0.14

 ç½

0.14

ryan

0.14

 Batter

0.14

odal

0.13

 pile

0.13

ãģĤ

0.13

Activations Density 0.095%

names and terms related to authors and their works

No Comments

No Known Activations