INDEX

Explanations

terms related to programming functions and system calls

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

Trace

-0.15

ths

-0.14

wang

-0.14

ubre

-0.14

upert

-0.14

Ã¤re

-0.14

.addElement

-0.14

ilm

-0.13

ostÃŃ

-0.13

 Katy

-0.13

POSITIVE LOGITS

0.16

kov

0.16

é¾Ħ

0.15

Ø§ÙħÛĮ

0.15

dbus

0.14

.tc

0.14

į°ìĿ´

0.14

divid

0.14

buat

0.13

Activations Density 0.152%

terms related to programming functions and system calls

No Comments

No Known Activations