INDEX

Explanations

phrases related to acquiring information or learning opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

$__

-0.16

ALIGN

-0.14

 Sass

-0.14

urge

-0.14

dba

-0.14

 vá»įng

-0.14

Ø¯Ø§Ø±

-0.13

.pan

-0.13

mighty

-0.13

istinguished

-0.13

POSITIVE LOGITS

 details

0.19

 Details

0.18

annel

0.17

raquo

0.17

 >↵

0.17

opens

0.17

 DETAILS

0.17

>>↵

0.16

>↵

0.16

 è©³ç´°

0.15

Activations Density 0.214%

phrases related to acquiring information or learning opportunities

No Comments

No Known Activations