INDEX

Explanations

references to editorial roles or positions within a publication

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

-Sah

-0.17

ensa

-0.15

GROUND

-0.14

çĵ¶

-0.14

Ð¸ÐºÐ¸

-0.14

actics

-0.14

ãĥĥãĤ¯

-0.14

ħĮ

-0.14

elters

-0.14

POSITIVE LOGITS

ossal

0.16

äºķ

0.16

alore

0.15

 luder

0.15

amar

0.15

ouce

0.15

iface

0.15

swagger

0.15

OLF

0.14

yt

0.14

Activations Density 0.040%

references to editorial roles or positions within a publication

No Comments

No Known Activations