INDEX

Explanations

keywords related to questions and updates in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.16

utt

-0.15

sWith

-0.15

-0.14

.debian

-0.14

rog

-0.14

 Patri

-0.14

POSITIVE LOGITS

CDATA

0.17

tainment

0.15

EEP

0.15

Ð°Ð´Ð¶

0.14

HB

0.14

ãĥĶãĥ¼

0.14

à¸Ńà¸Ķ

0.13

adge

0.13

@js

0.13

"is

0.13

Activations Density 0.137%

keywords related to questions and updates in various contexts

No Comments

No Known Activations