INDEX

Explanations

references to notable individuals or roles related to academia and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 prive

-0.13

arence

-0.13

<--

-0.13

’aut

-0.13

 african

-0.12

 nonprofit

-0.12

bourne

-0.12

 lowercase

-0.12

...↵↵↵

-0.12

ÑĢÐ°Ñģ

-0.12

POSITIVE LOGITS

 Iranians

0.19

 Honour

0.19

 Israelis

0.19

 honour

0.18

;'

0.18

USA

0.18

 Juda

0.18

 whilst

0.18

0.17

 Obama

0.17

Activations Density 0.003%

references to notable individuals or roles related to academia and media

No Comments

No Known Activations