INDEX

Explanations

names of individuals and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Haskell

-0.19

vez

-0.15

Sty

-0.14

Dispose

-0.14

yz

-0.14

oire

-0.14

ICO

-0.14

.har

-0.14

TTY

-0.14

Leod

-0.14

POSITIVE LOGITS

 Nigerian

0.18

Gaw

0.17

 Nigeria

0.17

µľ

0.16

ÙĦÙĬÙĩ

0.15

gba

0.15

ÏĦÎµÏģ

0.15

Amb

0.14

OPY

0.14

olut

0.14

Activations Density 0.055%

names of individuals and their affiliations

No Comments

No Known Activations