INDEX

Explanations

geographic locations and institutional names

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

 denomin

-0.18

YC

-0.17

 denom

-0.16

OBS

-0.15

idon

-0.15

 Tobias

-0.15

assin

-0.14

kit

-0.14

 Bison

-0.14

.AI

-0.14

POSITIVE LOGITS

 Weber

0.23

aday

0.18

iggs

0.18

0.17

 Hatch

0.17

 Hunts

0.17

 Uint

0.17

poly

0.16

 Utah

0.16

angu

0.16

Activations Density 0.034%

geographic locations and institutional names

No Comments

No Known Activations