INDEX

Explanations

references to chaplains and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

essel

-0.16

izzato

-0.16

pitch

-0.15

Ã¼f

-0.15

orf

-0.15

Ã¶n

-0.15

es

-0.14

rib

-0.14

entifier

-0.14

ously

-0.14

POSITIVE LOGITS

lain

0.29

chap

0.23

 chap

0.22

itre

0.20

 Chap

0.19

anooga

0.18

Stick

0.18

AGAIN

0.18

elize

0.18

lin

0.17

Activations Density 0.004%

references to chaplains and related terminology

No Comments

No Known Activations