INDEX

Explanations

references to specific locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

inki

-0.17

 Floyd

-0.16

XR

-0.16

FLT

-0.15

ermann

-0.15

enser

-0.15

 Kentucky

-0.15

allon

-0.15

antic

-0.15

pun

-0.14

POSITIVE LOGITS

 Cleveland

0.26

 Durham

0.24

 Scarborough

0.20

 Sunderland

0.20

leveland

0.20

Dur

0.18

dur

0.16

auga

0.16

NEO

0.15

 steel

0.15

Activations Density 0.062%

references to specific locations and institutions

No Comments

No Known Activations