INDEX

Explanations

punctuation marks and symbols in structured data or code context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ing

-0.21

ingo

-0.19

.bd

-0.15

Ãłng

-0.14

ING

-0.13

æĹı

-0.13

InnerText

-0.13

 eagle

-0.13

ias

-0.13

POSITIVE LOGITS

uteur

0.15

ihan

0.15

bart

0.14

osto

0.14

igrate

0.14

ExecutionContext

0.14

Tester

0.14

vÃ©

0.14

CHK

0.14

baar

0.13

Activations Density 0.015%

punctuation marks and symbols in structured data or code context

No Comments

No Known Activations