INDEX

Explanations

Associated Press (AP) references in news articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

.IContainer

-0.16

ienes

-0.16

ynom

-0.14

uegos

-0.14

istÃ©

-0.14

sse

-0.13

isas

-0.13

ÃŃme

-0.13

ymous

-0.13

ollah

-0.13

POSITIVE LOGITS

Ĭ

0.16

 vice

0.14

 Washer

0.14

TMP

0.14

obsolete

0.14

 æ±

0.13

anges

0.13

 bene

0.13

vtk

0.12

 Wahl

0.12

Activations Density 0.002%

Associated Press (AP) references in news articles

No Comments

No Known Activations