INDEX

Explanations

phrases indicating requests for user reviews and testimonials

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

 Torch

-0.16

ÄĻd

-0.15

-0.14

 accompagn

-0.14

 Peaks

-0.14

 Brow

-0.14

AAA

-0.14

ival

-0.14

iller

-0.14

/MIT

-0.14

POSITIVE LOGITS

udu

0.17

Subsystem

0.16

ultipart

0.15

oldem

0.15

quez

0.14

ÑıÑĩ

0.14

 pisc

0.14

zos

0.14

ertos

0.14

cplusplus

0.14

Activations Density 0.027%

phrases indicating requests for user reviews and testimonials

No Comments

No Known Activations