INDEX

Explanations

symbols, punctuation, and formatting elements in text

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

-0.17

.TabStop

-0.16

-0.15

/REC

-0.15

iller

-0.15

grave

-0.15

-0.14

ertools

-0.14

arel

-0.14

gnore

-0.14

POSITIVE LOGITS

0.42

0.40

0.31

0.30

--------------------

0.26

↵

0.24

                    č↵

0.24

 --------------------

0.23

↵                    ↵

0.23

................

0.22

Activations Density 0.005%

symbols, punctuation, and formatting elements in text

No Comments

No Known Activations