INDEX

Explanations

references to the author Nicholas Schaffner

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

igmat

-0.15

isel

-0.15

Ø¹Ø§Ùħ

-0.15

 ÄĮer

-0.15

-0.14

imei

-0.14

æŁĦ

-0.14

Ã©ny

-0.14

anz

-0.14

ardown

-0.14

POSITIVE LOGITS

orno

0.15

ì£½

0.14

odÃŃ

0.14

inton

0.14

ouri

0.14

icans

0.14

rocket

0.14

ius

0.14

ocab

0.13

 typename

0.13

Activations Density 0.009%

references to the author Nicholas Schaffner

No Comments

No Known Activations