INDEX

Explanations

references to the Apache software foundation or its projects

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

rica

-0.15

.Xaml

-0.15

swick

-0.15

.scalablytyped

-0.15

 Dare

-0.15

APTER

-0.15

rana

-0.14

idel

-0.14

isz

-0.14

enschaft

-0.14

POSITIVE LOGITS

æ®µ

0.15

iage

0.14

uhn

0.14

BTN

0.13

ãĥĨãĥ«

0.13

ì½

0.13

erialized

0.13

ingers

0.13

uluk

0.13

UTOR

0.13

Activations Density 0.007%

references to the Apache software foundation or its projects

No Comments

No Known Activations