INDEX

Explanations

references to prior research or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iez

-0.18

SCP

-0.16

rosso

-0.16

-addons

-0.15

æľĹ

-0.15

Ìģ

-0.15

inch

-0.15

AGO

-0.14

styleType

-0.14

imli

-0.14

POSITIVE LOGITS

 doom

0.15

ousel

0.15

 Vict

0.14

.scalablytyped

0.14

ÙĬØ¯Ø©

0.14

afort

0.14

klÃ¤

0.14

nier

0.13

ÐºÐ¼

0.13

 Sent

0.13

Activations Density 0.031%

references to prior research or citations

No Comments

No Known Activations