INDEX

Explanations

distinct structural elements or symbols typically found in programming or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ĶåĽŀ

-0.17

Erg

-0.15

"'

-0.14

/core

-0.14

prise

-0.13

unge

-0.13

blank

-0.13

eil

-0.13

 Equip

-0.13

 =>↵

-0.13

POSITIVE LOGITS

--

0.32

--*/↵

0.30

--

0.29

(--

0.27

'--

0.25

--){↵

0.24

--)↵

0.24

--;↵

0.24

--,

0.24

--č↵

0.23

Activations Density 0.081%

distinct structural elements or symbols typically found in programming or mathematical expressions

No Comments

No Known Activations