INDEX

Explanations

numerical data and formatting, particularly related to dates and versions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

azen

-0.15

Bindable

-0.15

ãĥ³ãĥĢ

-0.15

gmt

-0.14

indy

-0.14

Dep

-0.14

unk

-0.14

undai

-0.14

wins

-0.14

nota

-0.13

POSITIVE LOGITS

elper

0.16

ertest

0.16

 '\''

0.15

imeline

0.14

uet

0.14

[opt

0.14

iard

0.14

compileComponents

0.14

Rgb

0.14

atters

0.14

Activations Density 0.078%

numerical data and formatting, particularly related to dates and versions

No Comments

No Known Activations