INDEX

Explanations

locations and names of places

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

/resource

-0.15

pers

-0.15

Ñĵ

-0.15

elan

-0.14

 Baltimore

-0.14

 TForm

-0.14

asta

-0.14

-Sah

-0.13

 hete

-0.13

anka

-0.13

POSITIVE LOGITS

 Berkshire

0.33

 Windsor

0.28

 Maiden

0.25

Asc

0.23

 Thames

0.22

 Reading

0.21

Asc

0.20

 Sind

0.20

Sl

0.19

 Tile

0.19

Activations Density 0.022%

locations and names of places

No Comments

No Known Activations