INDEX

Explanations

content related to tasks and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Goth

-0.15

Contents

-0.15

 transit

-0.14

 canon

-0.14

Tal

-0.14

 Ø§ÙĦØ¹ÙĤ

-0.14

indy

-0.14

yen

-0.13

 Talent

-0.13

COOKIE

-0.13

POSITIVE LOGITS

.crm

0.17

TRS

0.16

ovu

0.15

ertino

0.15

abase

0.15

aeper

0.15

.googlecode

0.14

tright

0.14

ephir

0.14

Activations Density 0.029%

content related to tasks and responsibilities

No Comments

No Known Activations