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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ehler

-0.17

 ØªØ§

-0.17

-to

-0.17

ë¶ĢíĦ°

-0.14

èĩ³

-0.14

åĪ°

-0.14

AsString

-0.13

åĪ°äºĨ

-0.13

 åĪ°

-0.13

POSITIVE LOGITS

 inclusive

0.36

inclusive

0.32

 inclus

0.28

clusive

0.22

 period

0.22

 arasÄ±

0.18

 respectively

0.17

 periods

0.17

period

0.17

 Period

0.15

Activations Density 0.181%

dates and time references

No Comments

No Known Activations

dates and time references

No Comments

No Known Activations