INDEX

Explanations

phrases indicating conditions or qualities that are not satisfactory or surprising

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ser

-0.17

 nedir

-0.16

cher

-0.15

ãģıãģł

-0.15

assin

-0.15

cho

-0.14

Ð¾Ð¶

-0.14

VR

-0.14

raj

-0.14

POSITIVE LOGITS

ÏĦÏİ

0.15

ÐĲÑĢÑħÑĸÐ²

0.15

argo

0.15

arih

0.14

ebek

0.14

irected

0.14

 Ukraj

0.14

istrovstvÃŃ

0.14

 newName

0.14

Ãºb

0.14

Activations Density 0.241%

phrases indicating conditions or qualities that are not satisfactory or surprising

No Comments

No Known Activations