INDEX

Explanations

references to specific time durations and quantities, often in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

opleft

-0.18

yen

-0.15

sey

-0.14

regunta

-0.14

bah

-0.14

Ø¯Ø±

-0.13

avier

-0.13

.twimg

-0.13

figcaption

-0.13

POSITIVE LOGITS

ago

0.27

 interval

0.21

 span

0.20

ago

0.20

 ná»¯a

0.20

Ago

0.20

 Ð½Ð°Ð·Ð°Ð´

0.20

-old

0.18

 passed

0.18

 validity

0.16

Activations Density 0.109%

references to specific time durations and quantities, often in a structured context

No Comments

No Known Activations