INDEX

Explanations

code elements and attributes within programming and scripting contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ennen

-0.19

duto

-0.15

obil

-0.15

Ãłm

-0.14

 participates

-0.14

pek

-0.14

 participation

-0.14

Ãºsqueda

-0.14

conn

-0.14

marsh

-0.14

POSITIVE LOGITS

0.14

Ð¾Ð»Ð¾Ñģ

0.14

 collateral

0.14

.setter

0.14

0.13

loud

0.13

Ø¨Ø§ÙĨ

0.13

 dish

0.13

 Dive

0.13

ÑıÐ¶

0.13

Activations Density 3.143%

code elements and attributes within programming and scripting contexts

No Comments

No Known Activations