INDEX

Explanations

programming-related terms and structures in code, particularly focusing on selectors and elements

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

 Babe

-0.15

iqu

-0.15

amel

-0.15

ih

-0.15

ardi

-0.15

ule

-0.15

endi

-0.15

jist

-0.14

HC

-0.14

ung

-0.14

POSITIVE LOGITS

(æ°´

0.18

name

0.15

(æĹ¥

0.15

.structure

0.14

ryn

0.14

Dlg

0.14

Ú¯Ø§ÙĨÛĮ

0.14

lisi

0.14

eyin

0.14

Activations Density 0.054%

programming-related terms and structures in code, particularly focusing on selectors and elements

No Comments

No Known Activations