INDEX

Explanations

references to the Himalayas and associated geographical features

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

holm

-0.18

iked

-0.16

 plage

-0.15

 samo

-0.15

 Plains

-0.15

 Beach

-0.14

ekil

-0.14

 beach

-0.14

templ

-0.14

ÑĢÐ¾Ð±

-0.14

POSITIVE LOGITS

 mountains

0.36

 Mountains

0.33

 footh

0.28

 mountain

0.27

 Alps

0.24

-mount

0.22

mount

0.22

å±±

0.21

 Mountain

0.19

Mount

0.19

Activations Density 0.035%

references to the Himalayas and associated geographical features

No Comments

No Known Activations