INDEX

Explanations

HTML elements and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icut

-0.16

åĸĦ

-0.15

ipo

-0.15

esson

-0.15

ipeg

-0.15

Ð¸Ð½ÑĥÐ²

-0.15

 Compound

-0.15

dre

-0.14

enek

-0.14

arme

-0.14

POSITIVE LOGITS

 points

0.15

yr

0.14

ael

0.14

[#

0.14

eb

0.14

igo

0.14

à¸ķà¸°

0.13

ullo

0.13

 definition

0.13

 Pets

0.13

Activations Density 0.007%

HTML elements and their attributes

No Comments

No Known Activations