INDEX

Explanations

phrases indicating causality or reasons for events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

eb

-0.16

ones

-0.15

Ī

-0.15

rippling

-0.14

emean

-0.14

ertz

-0.14

èģ²

-0.14

ayaran

-0.13

Îŀ

-0.13

ppard

-0.13

POSITIVE LOGITS

ammer

0.15

CEE

0.14

oret

0.14

ocre

0.14

sted

0.14

DataContract

0.13

dio

0.13

gate

0.13

Activations Density 0.064%

phrases indicating causality or reasons for events

No Comments

No Known Activations