INDEX

Explanations

references to the term "du" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

rim

-0.17

ured

-0.16

gio

-0.14

Ã¼b

-0.14

omor

-0.14

neider

-0.14

rimp

-0.14

ukes

-0.14

 missing

-0.14

layan

-0.14

POSITIVE LOGITS

ovny

0.17

Dud

0.17

amel

0.16

CSI

0.16

eldorf

0.15

chod

0.15

cis

0.15

_EXTERNAL

0.15

PLICATE

0.14

lex

0.14

Activations Density 0.093%

references to the term "du" and its variations in different contexts

No Comments

No Known Activations