INDEX

Explanations

references to Boston and locations associated with it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

orre

-0.19

alat

-0.19

HLT

-0.18

chas

-0.16

sert

-0.16

vre

-0.15

 Connecticut

-0.15

 Township

-0.15

lingen

-0.15

¦

-0.14

POSITIVE LOGITS

 Back

0.23

Fen

0.22

 Trem

0.21

 Char

0.21

Zak

0.20

 Jamaica

0.19

TD

0.19

 Kendall

0.19

Ale

0.19

 Carson

0.19

Activations Density 0.018%

references to Boston and locations associated with it

No Comments

No Known Activations