INDEX

Explanations

references to business sectors and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

uls

-0.16

illo

-0.15

-0.14

qv

-0.14

Carthy

-0.14

 Protected

-0.13

Ð½Ð¾Ð¶

-0.13

annel

-0.13

,...↵↵

-0.13

Bri

-0.13

POSITIVE LOGITS

igger

0.15

ountain

0.14

ahu

0.14

posable

0.13

ournaments

0.13

elp

0.13

å®Ŀ

0.13

CB

0.13

_argument

0.13

 verg

0.13

Activations Density 0.022%

references to business sectors and related terms

No Comments

No Known Activations