INDEX

Explanations

references to specific locations or contexts within various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 entirety

-0.16

 accordingly

-0.16

 other

-0.15

à¸ķà¸¥à¸Ńà¸Ķ

-0.15

 elsewhere

-0.15

trs

-0.15

TECTED

-0.15

igan

-0.14

ODO

-0.14

 worldwide

-0.14

POSITIVE LOGITS

 ones

0.22

 those

0.22

those

0.18

éĤ£äºĽ

0.18

ones

0.18

ÏĦÎ¯

0.17

 tÄĽch

0.16

ijken

0.16

 especially

0.15

Those

0.15

Activations Density 0.209%

references to specific locations or contexts within various subjects

No Comments

No Known Activations