INDEX

Explanations

phrases or expressions indicating the act of bringing up a topic or issue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

prit

-0.15

ÙĪØªØ±

-0.15

igg

-0.15

 queryInterface

-0.14

ijkstra

-0.14

 strap

-0.14

amarin

-0.14

eprom

-0.14

astle

-0.14

ÙĴÙĩ

-0.14

POSITIVE LOGITS

xFFF

0.17

vement

0.16

Mixin

0.15

ColumnInfo

0.15

ì¹¨

0.15

uerdo

0.14

datable

0.14

aje

0.14

sumer

0.14

ancellable

0.14

Activations Density 0.007%

phrases or expressions indicating the act of bringing up a topic or issue

No Comments

No Known Activations