INDEX

Explanations

references to academic names or institutions related to research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 -*-č↵

-0.15

stub

-0.15

èĭ±éĽĦ

-0.15

etta

-0.14

atab

-0.14

rung

-0.14

cip

-0.14

/Form

-0.14

Î¹ÏĥÏĦÎ¿

-0.13

ulumi

-0.13

POSITIVE LOGITS

avor

0.15

aires

0.15

orton

0.14

iosis

0.14

xed

0.14

 Abstract

0.14

 Clown

0.14

 alarm

0.14

Abstract

0.13

 Alarm

0.13

Activations Density 0.040%

references to academic names or institutions related to research studies

No Comments

No Known Activations