INDEX

Explanations

the phrase "After" followed by numbers or related activations indicating occurrences or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

vik

-0.14

illing

-0.14

lio

-0.14

à¤¾à¤¹

-0.14

ê°Ħ

-0.14

 refined

-0.13

rome

-0.13

azole

-0.13

uki

-0.13

POSITIVE LOGITS

words

0.16

Dob

0.16

ward

0.15

noon

0.15

abbo

0.15

wards

0.15

word

0.14

æ¸Ī

0.14

AREST

0.14

 ÃĸÄŁ

0.14

Activations Density 0.048%

the phrase "After" followed by numbers or related activations indicating occurrences or events

No Comments

No Known Activations