INDEX

Explanations

dates and time references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.16

eru

-0.15

entin

-0.15

 å¡

-0.15

ripp

-0.15

-0.14

aches

-0.14

arts

-0.14

ÑĢÑİ

-0.13

hari

-0.13

POSITIVE LOGITS

ourg

0.17

 dikke

0.15

Ã¼ÄŁ

0.14

odnÃŃ

0.14

ãĥ³ãĤ¬

0.14

HashCode

0.14

Kel

0.13

 Woodward

0.13

ADDE

0.13

mise

0.13

Activations Density 0.035%

dates and time references

No Comments

No Known Activations