INDEX

Explanations

mathematical notations and programming expressions

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

 ÑĥÐ¶

-0.16

cak

-0.15

oin

-0.15

thenReturn

-0.14

 Skyl

-0.14

Nib

-0.14

iteli

-0.13

ÐºÐ°Ð²

-0.13

 OnCollision

-0.13

POSITIVE LOGITS

iban

0.16

arium

0.16

 Void

0.16

ein

0.16

umen

0.14

adel

0.14

pell

0.14

geb

0.14

 VOID

0.14

iveau

0.14

Activations Density 0.009%

mathematical notations and programming expressions

No Comments

No Known Activations