INDEX

Explanations

references to programming constructs and exceptions in code documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.Aggressive

-0.15

istrovstvÃŃ

-0.14

agit

-0.14

ventory

-0.14

QRS

-0.13

ANJI

-0.13

à¸°

-0.13

oppel

-0.13

FolderPath

-0.13

\b

-0.13

POSITIVE LOGITS

roma

0.15

wald

0.15

anean

0.14

 McGu

0.14

esome

0.13

handler

0.13

icter

0.13

prÃ¼

0.13

ylon

0.13

Activations Density 0.160%

references to programming constructs and exceptions in code documentation

No Comments

No Known Activations