INDEX

Explanations

corporate entities and their associated abbreviations

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

 verst

-0.16

baugh

-0.16

elow

-0.15

hone

-0.15

rone

-0.15

poz

-0.15

çĲ³

-0.14

 Î»Î±

-0.14

vier

-0.14

dy

-0.14

POSITIVE LOGITS

odic

0.17

ĺħ

0.16

stanov

0.16

luet

0.15

ild

0.14

ataka

0.14

ANNOT

0.14

Î»ÎµÎº

0.14

uncio

0.14

iken

0.13

Activations Density 0.010%

corporate entities and their associated abbreviations

No Comments

No Known Activations