INDEX

Explanations

structures commonly found in programming code, particularly assignment or initialization statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ainen

-0.16

reau

-0.14

ľĺ

-0.14

com

-0.14

ãĤĪ

-0.14

ibold

-0.14

Ø³Ø·Ø³

-0.14

PTR

-0.14

_INTR

-0.13

POSITIVE LOGITS

ÐµÐ½Ð½Ñĸ

0.15

Ø¯Ø±ÛĮ

0.14

Ð°ÑĢÑı

0.14

udios

0.14

 Pink

0.14

ÏĩÎ¿

0.14

ente

0.13

anger

0.13

loat

0.13

 pushViewController

0.13

Activations Density 0.001%

structures commonly found in programming code, particularly assignment or initialization statements

No Comments

No Known Activations