INDEX

Explanations

dates and temporal markers that indicate specific timeframes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

umb

-0.15

 upstream

-0.15

llib

-0.14

_between

-0.14

 sooner

-0.14

Äĵ

-0.14

ynet

-0.13

ioni

-0.13

Between

-0.13

vÃ©

-0.13

POSITIVE LOGITS

 forward

0.57

 onwards

0.53

 onward

0.50

Forward

0.49

 Forward

0.49

forward

0.49

_forward

0.42

 FORWARD

0.42

-forward

0.42

.forward

0.42

Activations Density 0.166%

dates and temporal markers that indicate specific timeframes

No Comments

No Known Activations