INDEX

Explanations

phrases and terminology associated with formal or academic writing, particularly in contexts related to regulations or guidelines

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

_TestCase

-0.16

 chiff

-0.15

haft

-0.14

reira

-0.14

readcr

-0.14

 Schiff

-0.14

íıĲ

-0.14

veillance

-0.14

anine

-0.14

POSITIVE LOGITS

±

0.15

itu

0.14

phans

0.14

onna

0.14

chema

0.14

 Tomorrow

0.14

è¾

0.13

 Pieces

0.13

zn

0.13

uju

0.13

Activations Density 0.422%

phrases and terminology associated with formal or academic writing, particularly in contexts related to regulations or guidelines

No Comments

No Known Activations