INDEX

Explanations

references to the year 197

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

amo

-0.18

adge

-0.17

halb

-0.16

 herr

-0.16

ìłĪ

-0.15

ingly

-0.15

ILON

-0.15

æµİ

-0.15

orp

-0.14

adio

-0.14

POSITIVE LOGITS

avers

0.19

ammers

0.17

riday

0.17

asso

0.16

inz

0.15

ometown

0.15

brew

0.15

jem

0.15

inged

0.15

oes

0.15

Activations Density 0.018%

references to the year 197

No Comments

No Known Activations