INDEX

Explanations

references to collective actions or community statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

argo

-0.17

reachable

-0.15

ylie

-0.15

.icons

-0.15

 Favor

-0.15

elper

-0.14

suming

-0.14

plat

-0.14

 butt

-0.14

AFX

-0.14

POSITIVE LOGITS

 couldn

0.25

couldn

0.23

 Couldn

0.23

are

0.20

 feel

0.19

 proud

0.19

 congr

0.19

 happy

0.18

 sÄħ

0.18

be

0.18

Activations Density 0.103%

references to collective actions or community statements

No Comments

No Known Activations