INDEX

Explanations

associations with the concept of familiarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

(with

-0.17

 ÑģÐ¾

-0.16

—with

-0.15

chine

-0.15

orget

-0.14

mens

-0.14

ifr

-0.14

cores

-0.14

os

-0.14

prite

-0.14

POSITIVE LOGITS

wt

0.21

iw

0.20

wir

0.17

ĮĴ

0.15

jem

0.15

 whit

0.15

wd

0.15

 Bylo

0.15

 will

0.15

ith

0.14

Activations Density 0.117%

associations with the concept of familiarity

No Comments

No Known Activations