INDEX

Explanations

dates and temporal expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-0.22

-0.21

-0.19

 COVID

-0.19

-0.18

COVID

-0.17

Û±Û¹Û¹

-0.17

 Covid

-0.17

POSITIVE LOGITS

0.33

Û²Û°Û±

0.22

 Obama

0.22

Obama

0.21

0.20

 Twelve

0.19

0.18

 Barack

0.18

0.17

Activations Density 0.088%

dates and temporal expressions

No Comments

No Known Activations