INDEX

Explanations

references to media releases and announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

pon

-0.15

oola

-0.15

ething

-0.14

ãĥīãĥ«

-0.14

neh

-0.14

åĬł

-0.14

andel

-0.13

æ¢¨

-0.13

ampp

-0.13

Insets

-0.12

POSITIVE LOGITS

oreach

0.17

oppins

0.16

ABCDEFG

0.14

TestCategory

0.14

abcdefghijkl

0.14

hcp

0.14

Ell

0.14

ynet

0.14

stem

0.13

DataContract

0.13

Activations Density 0.031%

references to media releases and announcements

No Comments

No Known Activations