INDEX

Explanations

elements related to product features and benefits

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

Ã´n

-0.17

arkin

-0.16

 Berm

-0.16

usi

-0.15

 bern

-0.15

ToDevice

-0.15

 Barker

-0.14

DMA

-0.14

 intermediary

-0.14

tri

-0.14

POSITIVE LOGITS

 alike

0.19

nal

0.16

:animated

0.15

aload

0.15

abase

0.15

prung

0.14

agr

0.13

acle

0.13

atte

0.13

.joda

0.13

Activations Density 0.114%

elements related to product features and benefits

No Comments

No Known Activations