INDEX

Explanations

mathematical notation and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ych

-0.17

ikit

-0.15

lfw

-0.15

ennen

-0.15

Ø©

-0.13

reich

-0.13

ÄĽn

-0.13

yclic

-0.13

okable

-0.13

åº

-0.13

POSITIVE LOGITS

[-

0.23

*[

0.19

%\

0.18

vana

0.15

udeau

0.15

umber

0.15

otte

0.14

*↵

0.14

iverz

0.14

Activations Density 0.020%

mathematical notation and formatting

No Comments

No Known Activations