INDEX

Explanations

programming language syntax and key terms related to Java and MathML

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

æĪ¶

-0.16

rum

-0.15

urs

-0.14

çıŃ

-0.14

 Albert

-0.14

.gif

-0.14

lay

-0.14

 Frontier

-0.14

 Morton

-0.14

Kid

-0.14

POSITIVE LOGITS

yon

0.16

ģµ

0.14

ua

0.14

ÐµÑģÑı

0.14

libc

0.14

aison

0.14

agina

0.13

inear

0.13

/apt

0.13

ssh

0.13

Activations Density 0.025%

programming language syntax and key terms related to Java and MathML

No Comments

No Known Activations