INDEX

Explanations

requests for information and details about various topics and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

onth

-0.15

-0.14

eos

-0.14

ÙĨÙĪØ¹

-0.14

æĶ

-0.13

.AppendFormat

-0.13

enance

-0.13

rome

-0.13

LOUD

-0.13

infra

-0.13

POSITIVE LOGITS

 yourself

0.17

 Pend

0.15

 nhÃ©

0.14

quo

0.14

unas

0.14

.enqueue

0.14

adb

0.14

 Yourself

0.14

ãĥ¼ãĤ¿

0.13

etim

0.13

Activations Density 0.109%

requests for information and details about various topics and services

No Comments

No Known Activations