INDEX

Explanations

actions taken by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

CHED

-0.14

Ð½ÑıÑĤ

-0.14

Scalars

-0.14

Permanent

-0.14

itus

-0.14

omer

-0.13

Pom

-0.13

 totiÅ¾

-0.13

au

-0.13

ulin

-0.13

POSITIVE LOGITS

strup

0.18

 pant

0.17

isque

0.15

ippers

0.14

 sorte

0.14

apg

0.14

urette

0.14

uddy

0.14

yor

0.13

 Impl

0.13

Activations Density 0.254%

actions taken by individuals

No Comments

No Known Activations