INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ibbon

-0.15

Ã¡v

-0.14

edef

-0.14

bane

-0.14

burgh

-0.14

eting

-0.14

ndo

-0.13

 Virt

-0.13

ordes

-0.13

POSITIVE LOGITS

osg

0.20

Ú¯Ø§ÙĩÛĮ

0.17

èĻ«

0.16

 Franti

0.16

"\↵

0.15

enth

0.15

 è©ķä¾¡

0.15

.Solid

0.14

illon

0.14

igation

0.14

Activations Density 0.035%

expressions of gratitude and appreciation

No Comments

No Known Activations