INDEX

Explanations

references to sections, parts, or components of a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ð¾Ñī

-0.16

INGER

-0.15

seau

-0.15

inger

-0.15

 hypers

-0.15

 ç¿

-0.15

 truth

-0.14

 pione

-0.14

ackbar

-0.14

makers

-0.14

POSITIVE LOGITS

OLEAN

0.15

YYY

0.15

imestep

0.14

senal

0.14

icipation

0.14

Ð¸Ð½Ñĸ

0.14

à¹Ģà¸Ļ

0.14

ä¹ĭä¸Ģ

0.14

elerik

0.14

Activations Density 0.055%

references to sections, parts, or components of a document

No Comments

No Known Activations