INDEX

Explanations

references to organizations and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

pte

-0.18

ongyang

-0.17

indow

-0.17

regnum

-0.17

uten

-0.15

esome

-0.15

isku

-0.15

ÑĤÐ°Ðº

-0.14

 Blasio

-0.14

ritten

-0.14

POSITIVE LOGITS

lify

0.14

ÐµÐºÑĤ

0.14

ph

0.14

çķ¶

0.13

 Amir

0.13

ÙĲÙħ

0.13

.VisualBasic

0.13

piring

0.13

 HERE

0.13

Activations Density 0.612%

references to organizations and their roles

No Comments

No Known Activations