INDEX

Explanations

mentions of leaks or rumors regarding technology products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ickerView

-0.15

Ī¬

-0.14

herits

-0.14

 oppon

-0.14

oksen

-0.14

veis

-0.14

ocket

-0.14

 ÑĥÑģÑĤÑĢÐ°

-0.13

icket

-0.13

zc

-0.13

POSITIVE LOGITS

.Networking

0.16

thr

0.14

ery

0.14

æ§

0.14

.endTime

0.14

LTR

0.13

uffman

0.13

pre

0.13

Activations Density 0.034%

mentions of leaks or rumors regarding technology products

No Comments

No Known Activations