INDEX

Explanations

instances of data manipulation and condition checking in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

eyen

-0.14

 Bucket

-0.14

 Ð²Ð½ÑĥÑĤ

-0.14

uzzle

-0.14

 intrinsic

-0.14

 -*-č↵

-0.13

 pong

-0.13

Ð²Ð¸Ñĩ

-0.13

asil

-0.13

uk

-0.13

POSITIVE LOGITS

uento

0.16

ting

0.15

llib

0.15

 Watt

0.14

ÅĤe

0.14

ered

0.14

icare

0.14

ÑĤÐµÑĢÐ½

0.14

oeff

0.14

affe

0.14

Activations Density 0.173%

instances of data manipulation and condition checking in code

No Comments

No Known Activations