INDEX

Explanations

technical terms and variables associated with scientific or structured contexts

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

okus

-0.18

etus

-0.16

ÙĪØ·

-0.15

ammers

-0.15

yc

-0.15

acia

-0.14

inyin

-0.14

å¹ħ

-0.14

aign

-0.14

POSITIVE LOGITS

tractor

0.17

ayacak

0.15

podob

0.14

ertools

0.14

.optString

0.14

 nosotros

0.14

Ð»Ð¸Ðº

0.14

MZ

0.14

ÄŁmen

0.14

_echo

0.13

Activations Density 0.022%

technical terms and variables associated with scientific or structured contexts

No Comments

No Known Activations