INDEX

Explanations

instances of events and their sequences over time

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

ghan

-0.15

unas

-0.15

-last

-0.15

 yesterday

-0.14

Ahead

-0.14

èĬ¯

-0.14

ches

-0.13

aley

-0.13

arest

-0.13

POSITIVE LOGITS

 later

0.53

 subsequent

0.51

 subsequently

0.49

later

0.43

Later

0.40

 Later

0.39

 next

0.35

 spÃ¤ter

0.35

 soon

0.34

 thereafter

0.34

Activations Density 0.337%

instances of events and their sequences over time

No Comments

No Known Activations