INDEX

Explanations

references to data processing and technical components related to software or hardware systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

-0.19

erp

-0.18

presso

-0.18

áº¥p

-0.17

hand

-0.17

OP

-0.17

er

-0.17

rs

-0.16

est

-0.16

POSITIVE LOGITS

artment

0.20

seudo

0.19

pler

0.19

seud

0.19

ocalypse

0.19

ster

0.18

licate

0.18

kins

0.18

.BorderSize

0.18

loid

0.17

Activations Density 0.781%

references to data processing and technical components related to software or hardware systems

No Comments

No Known Activations