INDEX

Explanations

references to agreements and regulations involving collaboration or governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Marino

-0.16

enders

-0.15

_INCLUDE

-0.15

\Api

-0.15

adele

-0.14

etre

-0.14

uÄį

-0.14

.slim

-0.14

coni

-0.14

emean

-0.14

POSITIVE LOGITS

cha

0.17

angent

0.16

arrant

0.15

UA

0.15

ait

0.15

rompt

0.15

ACHER

0.15

iner

0.15

0.14

Activations Density 0.020%

references to agreements and regulations involving collaboration or governance

No Comments

No Known Activations