INDEX

Explanations

references to academic positions and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ires

-0.20

 phÃŃa

-0.18

 fate

-0.17

 fiercely

-0.17

 vast

-0.17

leurs

-0.17

maktadÄ±r

-0.17

 frequent

-0.16

otos

-0.16

act

-0.16

POSITIVE LOGITS

gerald

0.21

inkel

0.21

amental

0.19

amentals

0.19

idious

0.18

onacci

0.18

-forward

0.18

bruary

0.17

egan

0.17

Activations Density 2.362%

references to academic positions and roles

No Comments

No Known Activations