INDEX

Explanations

references to numbers or numerical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

leÅŁik

-0.17

ä¸Ī

-0.15

 kÃ¼r

-0.15

icari

-0.15

 latter

-0.14

åĪļæīį

-0.14

radu

-0.14

å±Ĭ

-0.13

rego

-0.13

istique

-0.13

POSITIVE LOGITS

 bibli

0.16

0.15

↵↵

0.15

 Append

0.15

 append

0.15

âĢĥ

0.14

_:

0.14

Append

0.14

 Gutenberg

0.14

 Conclusion

0.14

Activations Density 0.054%

references to numbers or numerical concepts

No Comments

No Known Activations