INDEX

Explanations

occurrences of string-related terms and functions 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

åħ¶ä¸Ń

-0.17

ãģĬãĤĬ

-0.16

pcm

-0.16

cha

-0.15

MENT

-0.15

usa

-0.15

bsolute

-0.15

/student

-0.15

 serialVersionUID

-0.15

OwnProperty

-0.15

POSITIVE LOGITS

ified

0.24

.fromCharCode

0.20

sWith

0.18

(describing

0.18

.IsNullOrEmpty

0.17

.format

0.17

strup

0.16

cipher

0.16

bucks

0.16

fy

0.15

Activations Density 0.045%

occurrences of string-related terms and functions in code

No Comments

No Known Activations