INDEX

Explanations

strings related to errors and exceptions 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 @ 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

-0.15

of

-0.15

 aging

-0.15

or

-0.15

 string

-0.14

 being

-0.13

 with

-0.13

 Garn

-0.13

POSITIVE LOGITS

You

0.20

You

0.20

 There

0.18

Found

0.18

There

0.18

Got

0.18

got

0.18

Cannot

0.17

Please

0.17

Can

0.17

Activations Density 0.044%

strings related to errors and exceptions in code

No Comments

No Known Activations