INDEX

Explanations

references to specific geographical locations or regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÑĪÐ¸Ð±

-0.15

.Accessible

-0.15

Ult

-0.15

uela

-0.14

çĵľ

-0.14

 ìŀł

-0.14

Î¼ÎµÎ½

-0.14

 SÄ±r

-0.14

zim

-0.14

Msp

-0.14

POSITIVE LOGITS

ped

0.22

 branch

0.20

ped

0.20

Ped

0.19

Branch

0.19

 Branch

0.19

 Academy

0.18

 Mend

0.18

 State

0.17

 institute

0.17

Activations Density 0.058%

references to specific geographical locations or regions

No Comments

No Known Activations